# Open-Weight Models Under Apache License 2.0, Page 37 Source: https://savrn.com/models/licenses/apache-2-0/page/37 Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- SAVRN Model Hub · Models by License # Open-Weight Models Under Apache License 2.0 3,344 open-weight models released under Apache License 2.0 in the SAVRN Model Hub, with Team Mradermacher, Qwen and Google publishing the most. 3,344Models 1618Publishers 12K to 952.4BParameter range 1Licenses YesCommercial use ## What Apache License 2.0 Allows The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors. [Read the license text](https://www.apache.org/licenses/LICENSE-2.0). ## SAVRN's Take Apache 2.0 asks little of the operator. Commercial use, modification and redistribution are all permitted. What it requires is housekeeping: keep the license and copyright notices, carry any NOTICE file along with the weights, and state the significant changes if you pass a modified version on. It also includes an express patent grant from contributors, the clause a procurement reviewer looks for before a model serves paying customers. So an organization can take the files from the publisher, fine-tune on its own data, run the result in its own facility and bill for the output. On our hub 1,018 models carry this license. Qwen leads with 81, Google 50, Convergent Intelligence 39, PyTorch Image Models 32, OpenMed 31, Helsinki-NLP Research Group 27, and Unsloth AI and PaddlePaddle 22 each. Text generation accounts for 164 of the models, image and text to text for 89, and robotics for 43, so it covers more than chat. Downloads show where it runs. all-MiniLM-L6-v2 from Sentence Transformers, a 23M parameter sentence similarity model, pulls 255,050,544 downloads a month and needs 0.1 GB at 16-bit, small enough to ride on a GPU already serving. ms-marco-MiniLM-L6-v2 follows at 88,642,387 for text ranking. The one text generation model in the top eight is Qwen3-0.6B at 22,498,727 downloads a month: 752M parameters, a 40,960 token context, 1.8 GB at 16-bit, and the cheapest host on the Index for it is one MI300X at $1.85 an hour. SAVRN Research, 2026-09-18 ## Most Downloaded | Model | Publisher | Parameters | License | Monthly downloads | Cheapest GPUs at 16-bit | | --- | --- | --- | --- | --- | --- | | [all-MiniLM-L6-v2](https://savrn.com/models/all-minilm-l6-v2) | Sentence Transformers | 23M | apache-2.0 | 198.6M | 1x MI300X, $1.85/hr | | [ms-marco-MiniLM-L6-v2](https://savrn.com/models/ms-marco-minilm-l6-v2) | Sentence Transformers - Cross-Encoders | 23M | apache-2.0 | 73.1M | 1x MI300X, $1.85/hr | | [paraphrase-multilingual-MiniLM-L12-v2](https://savrn.com/models/paraphrase-multilingual-minilm-l12-v2) | Sentence Transformers | 118M | apache-2.0 | 41.9M | 1x MI300X, $1.85/hr | | [electra-base-discriminator](https://savrn.com/models/electra-base-discriminator) | Google | — | apache-2.0 | 38.9M | — | | [bert-base-uncased](https://savrn.com/models/bert-base-uncased) | BERT community | 110M | apache-2.0 | 28.9M | 1x MI300X, $1.85/hr | | [Qwen3-0.6B](https://savrn.com/models/qwen3-0-6b) | Qwen | 752M | apache-2.0 | 26.7M | 1x MI300X, $1.85/hr | | [t5-small](https://savrn.com/models/t5-small) | T5 community | 61M | apache-2.0 | 24.1M | 1x MI300X, $1.85/hr | | [all-mpnet-base-v2](https://savrn.com/models/all-mpnet-base-v2) | Sentence Transformers | 109M | apache-2.0 | 18.1M | 1x MI300X, $1.85/hr | | [mobilenetv3_small_100.lamb_in1k](https://savrn.com/models/mobilenetv3-small-100-lamb-in1k) | PyTorch Image Models | 3M | apache-2.0 | 17.7M | 1x MI300X, $1.85/hr | | [wav2vec2-large-xlsr-53-japanese](https://savrn.com/models/wav2vec2-large-xlsr-53-japanese) | Jonatas Grosman | — | apache-2.0 | 16M | — | ## Who Publishes Them | Publisher | Models | | --- | --- | | [Team Mradermacher](https://savrn.com/model-publishers/mradermacher) | 164 | | [Qwen](https://savrn.com/model-publishers/qwen) | 81 | | [Google](https://savrn.com/model-publishers/google) | 50 | | [Quan](https://savrn.com/model-publishers/wq2012) | 44 | | [RKNNAI](https://savrn.com/model-publishers/rknnai) | 43 | | [Convergent Intelligence](https://savrn.com/model-publishers/reaperdoesntknow) | 39 | ## All 3,344 Models, Page 37 of 56 Model ### [K2-Horizon-3.7B-heretic-xortron-GGUF](https://savrn.com/models/k2-horizon-3-7b-heretic-xortron-gguf) [Team Mradermacher](https://savrn.com/model-publishers/mradermacher) static quants of https://huggingface.co/darkc0de/K2-Horizon-3.7B-heretic-xortron For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants are available at https://huggingface.co/mradermacher/K2-Horizon-3.7B-heretic-xortron-i1-GGUF If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant And here are Artefact2's thoughts on the matter… Open weights apache-2.0 transformers [View model](https://savrn.com/models/k2-horizon-3-7b-heretic-xortron-gguf) Model · Text generation ### [K2-Horizon-3.7B-Q4_0-ARM-GGUF](https://savrn.com/models/k2-horizon-3-7b-q4-0-arm-gguf) [Matthew Broudy](https://savrn.com/model-publishers/bpmatt) every weight matrix, including the 250,624-token embedding table and output head, is Q40 (llama-quantize --pure), made from IFM's BF16 GGUF. The official GGUF repo has no Q40 file. On ARM CPUs with the i8mm or dotprod instructions llama.cpp runs Q40 faster than the K-quants: on a Snapdragon phone this file reads prompts 1.4-1.7x as fast as IFM's Q4KM, but generates only 1.04-1.11x as fast, and it is 9 % smaller. I tested it as an on-device chat model for an Android voice assistant (llama.cpp, CPU only). The file name follows the naming of IFM's GGUF repo (K2-Horizon-4B-.gguf). K2-Horizon family (3.7B core parameters plus a large vocabulary; 5.06B parameters in the file). All credit for the… Open weights apache-2.0 gguf [View model](https://savrn.com/models/k2-horizon-3-7b-q4-0-arm-gguf) Model ### [K2-Horizon-32B-heretic-i1-GGUF](https://savrn.com/models/k2-horizon-32b-heretic-i1-gguf) [Team Mradermacher](https://savrn.com/model-publishers/mradermacher) weighted/imatrix quants of https://huggingface.co/soyaakinohara/K2-Horizon-32B-heretic For a convenient overview and download list, visit our model page for this model. static quants are available at https://huggingface.co/mradermacher/K2-Horizon-32B-heretic-GGUF If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant And here are Artefact2's thoughts on the matter… Open weights apache-2.0 transformers [View model](https://savrn.com/models/k2-horizon-32b-heretic-i1-gguf) Model ### [K2-Horizon-7B-GGUF](https://savrn.com/models/k2-horizon-7b-gguf) [Team Mradermacher](https://savrn.com/model-publishers/mradermacher) static quants of https://huggingface.co/IFM/K2-Horizon-7B For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants are available at https://huggingface.co/mradermacher/K2-Horizon-7B-i1-GGUF If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 See… Open weights apache-2.0 transformers [View model](https://savrn.com/models/k2-horizon-7b-gguf) Model ### [K2-Horizon-7B-i1-GGUF](https://savrn.com/models/k2-horizon-7b-i1-gguf) [Team Mradermacher](https://savrn.com/model-publishers/mradermacher) weighted/imatrix quants of https://huggingface.co/IFM/K2-Horizon-7B For a convenient overview and download list, visit our model page for this model. static quants are available at https://huggingface.co/mradermacher/K2-Horizon-7B-GGUF If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 See… Open weights apache-2.0 transformers [View model](https://savrn.com/models/k2-horizon-7b-i1-gguf) Model ### [K2-Horizon-7B-MXFP8](https://savrn.com/models/k2-horizon-7b-mxfp8) [Use-AI](https://savrn.com/model-publishers/fp8enjoyer) MXFP8-quantized version of IFM/K2-Horizon-7B, targeting NVIDIA Blackwell GPUs. This repository provides an MXFP8 conversion of K2-Horizon-7B for use with block-scaled FP8 inference runtimes. The model weights were converted to MXFP8 using: - Blackwell-compatible block-scaled matrix multiplication The converted model contains approximately 254 MXFP8 modules. IFM/K2-Horizon-7B Please refer to the original model card for architecture details, training information, intended use, and limitations. The main quantized checkpoint is provided in SafeTensors format. Users should also obtain or use the corresponding configuration, tokenizer, and model architecture files from the original K2-Horizon-7B… Open weights apache-2.0 [View model](https://savrn.com/models/k2-horizon-7b-mxfp8) Model · Text generation ### [K2-Horizon-MoVA-36B-A4B-DERISKED-GGUF](https://savrn.com/models/k2-horizon-mova-36b-a4b-derisked-gguf) [Jackson](https://savrn.com/model-publishers/freakyskittle) GGUF conversions of Blackfrost-AI/K2-Horizon-MoVA-36B-A4B-DERISKED-BF16. The source is a weight-level behavioral derivative of IFM/K2-Horizon-MoVA-36B-A4B. DERISKED is the Blackfrost research label. It is not a claim of safety, zero refusals, or unchanged benchmark scores. Upstream llama.cpp cannot load k2-horizon. You need the IFM fork: https://github.com/MBZUAI-IFM/llama.cpp/tree/model/K2Horizon These files were converted and quantized with that branch at 42adf01. Host: Ryzen 6850H / Radeon 680M, Vulkan, GGMLVKDISABLEASYNC=1, fork build b1-42adf01. Prompt: The capital of France is, temperature 0, --jinja. IQ3M greedy sample (chat template, reasoning on): Routers (attnvgate) are kept in… Open weights apache-2.0 [View model](https://savrn.com/models/k2-horizon-mova-36b-a4b-derisked-gguf) Model · Text generation ### [K2-Horizon-MoVA-36B-A4B-NSLM-p4mx-q4v](https://savrn.com/models/k2-horizon-mova-36b-a4b-nslm-p4mx-q4v) [Matthew P Barnson](https://savrn.com/model-publishers/txgsync) An experimental NanoSeedLM (SeedLM) compression of IFM/K2-Horizon-MoVA-36B-A4B for Apple Silicon Macs with 32 GB of unified memory. SeedLM keeps each block of 8 weights as a 16-bit seed of a linear feedback shift register (LFSR), 4 coefficients and an exponent. The GPU makes the weights again from the seed at run time. The paper used an FPGA for this. This model uses Metal kernels on the Mac GPU. This is a research proof of concept. It is not a replacement for a calibrated quantization. - Six safetensors shards (22.76 GB in total, at most 4.5 GB each) and model.safetensors.index.json. The other files are config.json, the tokenizer files of the base model and nanoseedlmk2.py, the MLX loader.… Open weights apache-2.0 19.2B parameters 524,288 tokens mlx [View model](https://savrn.com/models/k2-horizon-mova-36b-a4b-nslm-p4mx-q4v) Model · Text generation ### [kairos-sotos-2.0-4B](https://savrn.com/models/kairos-sotos-2-0-4b) [Matheus Nery Walkowicz](https://savrn.com/model-publishers/walkowicz) Kairos Sotos 2.0 is an offline, autonomous cybersecurity and privacy code auditor fine-tuned from Qwen/Qwen3.5-4B. It reports the audit verdict, evidence, smallest safe remediation diff, and exact CWE along with versioned framework IDs. This repository hosts the full-precision BF16 (16-bit Brain Float) GGUF binary, preserving 100% of fine-tuned weight fidelity with zero quantization loss. 100% Consumer GPU Resident: At 8.4 GB, the entire unquantized model fits into a standard 12 GB VRAM consumer card (e.g. NVIDIA RTX 3060), leaving ~3.6 GB of VRAM headroom for up to 8,192 tokens of context without GPU memory thrashing or CPU offloading. 30% Size Reduction vs 1.0: Reduced file size from 12.0… Open weights apache-2.0 [View model](https://savrn.com/models/kairos-sotos-2-0-4b) Model · Text generation ### [kanana-1.5-8b-instruct-2505-Persona-Merge-K](https://savrn.com/models/kanana-1-5-8b-instruct-2505-persona-merge-k) [KIMsangen](https://savrn.com/model-publishers/egoigo) This llama model was trained 2x faster with Unsloth and Huggingface's TRL library. Open weights apache-2.0 8B parameters 32,768 tokens transformers [View model](https://savrn.com/models/kanana-1-5-8b-instruct-2505-persona-merge-k) Model · Text generation ### [kanana-1.5-8b-instruct-2505-Persona-Merged](https://savrn.com/models/kanana-1-5-8b-instruct-2505-persona-merged) [Jaehoon Song](https://savrn.com/model-publishers/luckysong777) This llama model was trained 2x faster with Unsloth and Huggingface's TRL library. Open weights apache-2.0 8B parameters 32,768 tokens transformers [View model](https://savrn.com/models/kanana-1-5-8b-instruct-2505-persona-merged) Model · Text generation ### [kanana-1.5-8b-instruct-2505-Persona-Merged](https://savrn.com/models/kanana-1-5-8b-instruct-2505-persona-merged-3) [Jihue](https://savrn.com/model-publishers/mgmbykai) This llama model was trained 2x faster with Unsloth and Huggingface's TRL library. Open weights apache-2.0 8B parameters 32,768 tokens transformers [View model](https://savrn.com/models/kanana-1-5-8b-instruct-2505-persona-merged-3) Model · Text generation ### [kanana-1.5-8b-instruct-2505-Persona-Merged](https://savrn.com/models/kanana-1-5-8b-instruct-2505-persona-merged-4) [Kihyun K](https://savrn.com/model-publishers/kihyun-k) This llama model was trained 2x faster with Unsloth and Huggingface's TRL library. Open weights apache-2.0 8B parameters 32,768 tokens transformers [View model](https://savrn.com/models/kanana-1-5-8b-instruct-2505-persona-merged-4) Model ### [karachi-aqi-predictor](https://savrn.com/models/karachi-aqi-predictor) [Aun](https://savrn.com/model-publishers/syed110-3) Open weights apache-2.0 [View model](https://savrn.com/models/karachi-aqi-predictor) Model · Text generation ### [Kataguru-Sceptic-Quality-Inspector-v1.0-NVFP4](https://savrn.com/models/kataguru-sceptic-quality-inspector-v1-0-nvfp4) [Jari Katajisto](https://savrn.com/model-publishers/kataguru) Kataguru Sceptic Quality Inspector v1.0 (NVFP4) is a sovereign, non-sycophantic LLM-as-a-Judge, automated dataset auditing engine, and high-throughput expert model built upon the Sparse Mixture-of-Experts (MoE) foundation of Kataguru Sceptic 35B-A3B (35 billion total parameters, 3 billion activated per token). Hardware-accelerated for NVIDIA RTX 50-series Blackwell architecture using native NVFP4 quantization (FP4 weights with FP8 activation scales), it achieves generation speeds of ~300–360 tok/s and an ultra-low ~70 ms Time To First Token (TTFT) while consuming only 12.1 GiB VRAM per GPU on dual RTX 5090 Blackwell hardware (TP=2). 1. Master Tri-Mode Operation: 2. Native Multimodal Vision… Open weights apache-2.0 36B parameters 262,144 tokens [View model](https://savrn.com/models/kataguru-sceptic-quality-inspector-v1-0-nvfp4) Model · Text generation ### [Kataguru-Sceptic-Quality-Inspector-v2.0-NVFP4](https://savrn.com/models/kataguru-sceptic-quality-inspector-v2-0-nvfp4) [Jari Katajisto](https://savrn.com/model-publishers/kataguru) Kataguru Sceptic Quality Inspector v2.0 (NVFP4) is a sovereign, non-sycophantic LLM-as-a-Judge, automated dataset auditing engine, and ultra-high-throughput expert model. Built upon the fleet-record foundation of Kataguru Sceptic Multi-Mode v2 CP1200 (72.01% multi-domain record, FAR = 0.000%) merged with the 16.4k certified forensic quality inspection task vector, it is purpose-engineered to serve as the fleet's primary data firewall and filtration engine. Hardware-optimized for NVIDIA RTX 50-series Blackwell architecture using native NVFP4 quantization (FP4 weights with FP8 activation scales), it achieves generation speeds of ~300–360 tok/s and an ultra-low ~70 ms Time To First Token… Open weights apache-2.0 36B parameters 262,144 tokens [View model](https://savrn.com/models/kataguru-sceptic-quality-inspector-v2-0-nvfp4) Model · Image and text to text ### [kb-qwen3.5-2b-4bit](https://savrn.com/models/kb-qwen3-5-2b-4bit) [Guodong Fei](https://savrn.com/model-publishers/kn90688) This model was converted to MLX format from Qwen/Qwen3.5-2B using mlx-vlm version 0.3.12. Refer to the original model card for more details on the model. Open weights apache-2.0 2.2B parameters 262,144 tokens transformers [View model](https://savrn.com/models/kb-qwen3-5-2b-4bit) Model ### [KenT_0.5B_Base](https://savrn.com/models/kent-0-5b-base) [Nguyễn Quôc Khánh](https://savrn.com/model-publishers/kenteake11) Model License: Apache 2.0; Training Data: Trained on Wikimedia Wikipedia.; Data License Notice: The original Wikipedia dataset is licensed under the Creative Commons Attribution-ShareAlike 4.0 International License (CC BY-SA 4.0).. Open weights apache-2.0 [View model](https://savrn.com/models/kent-0-5b-base) Model · Text generation ### [KenT_300M_Base](https://savrn.com/models/kent-300m-base) [Vietnam-LAB](https://savrn.com/model-publishers/vi-lab) Open weights apache-2.0 transformers [View model](https://savrn.com/models/kent-300m-base) Model · Text generation ### [KenT_400M_Base](https://savrn.com/models/kent-400m-base) [Vietnam-LAB](https://savrn.com/model-publishers/vi-lab) Open weights apache-2.0 399M parameters [View model](https://savrn.com/models/kent-400m-base) Model · Text generation ### [Keural-Cortex-8B-v1.0](https://savrn.com/models/keural-cortex-8b-v1-0) [MKD Co., Ltd.](https://savrn.com/model-publishers/mkd-dev) Open weights apache-2.0 8.2B parameters transformers [View model](https://savrn.com/models/keural-cortex-8b-v1-0) Model · Text generation ### [Keural-Cortex-8B-v1.0-1](https://savrn.com/models/keural-cortex-8b-v1-0-1) [Hika Dalju](https://savrn.com/model-publishers/hikaf143) Keural Cortex is MKD's local-first Korean-English language-model program for Keural applications. This release is an 8B-parameter, instruction- and preference-aligned checkpoint with a structured tool-calling layer for enterprise workflows. It is designed to run in customer-controlled infrastructure through an OpenAI-compatible vLLM endpoint. The host application—not the model—executes tools, enforces permissions, retrieves live data, and owns user data handling. English. Keural Cortex is a locally deployable AI foundation-model capability built for Korean-English enterprise interaction. It combines efficient 8B-scale inference, controllable OpenAI-compatible serving, and structured… Open weights apache-2.0 8.2B parameters 65,536 tokens transformers [View model](https://savrn.com/models/keural-cortex-8b-v1-0-1) Model · Text generation ### [Keural-MoE-14B](https://savrn.com/models/keural-moe-14b) [MKD Co., Ltd.](https://savrn.com/model-publishers/mkd-dev) Open weights apache-2.0 15.4B parameters transformers [View model](https://savrn.com/models/keural-moe-14b) Model · Text generation ### [Keural-Nova-1.0](https://savrn.com/models/keural-nova-1-0) [MKD Co., Ltd.](https://savrn.com/model-publishers/mkd-dev) Open weights apache-2.0 35.1B parameters transformers [View model](https://savrn.com/models/keural-nova-1-0) Model · Text generation ### [Keural-Nova-1.1](https://savrn.com/models/keural-nova-1-1) [MKD Co., Ltd.](https://savrn.com/model-publishers/mkd-dev) Open weights apache-2.0 35.1B parameters transformers [View model](https://savrn.com/models/keural-nova-1-1) Model · Text generation ### [Keural-Nova-v1.2-experimental](https://savrn.com/models/keural-nova-v1-2-experimental) [MKD Co., Ltd.](https://savrn.com/model-publishers/mkd-dev) Open weights apache-2.0 35.1B parameters transformers [View model](https://savrn.com/models/keural-nova-v1-2-experimental) Model · Text classification ### [kev-0.8b-code-verify-v1](https://savrn.com/models/kev-0-8b-code-verify-v1) [James](https://savrn.com/model-publishers/jtatman) A fine-tune of jaredpalmer/kev-0.8b (first fine-tune): a Jev-style decision model that judges whether code written by a cheap coding model is correct, so a router can keep the answer local or escalate it. One forward pass, a calibrated probability, no generated text. Trained on execution-labelled data: coder attempts at HumanEvalPack (Python) tasks, labelled by running each task's hidden test suite. The model never sees the hidden tests; its input is what a router can compute itself. The fine-tune binds these exact strings. One noul question (probability that the statement holds): State (an object; Kev renders it as key: value lines): generatededgecasetests comes from a small model writing… Open weights apache-2.0 peft [View model](https://savrn.com/models/kev-0-8b-code-verify-v1) Model · Text classification ### [kev-0.8b-code-verify-v2](https://savrn.com/models/kev-0-8b-code-verify-v2) [James](https://savrn.com/model-publishers/jtatman) A fine-tune of jaredpalmer/kev-0.8b (current best local judge: weak-coder data added): a Jev-style decision model that judges whether code written by a cheap coding model is correct, so a router can keep the answer local or escalate it. One forward pass, a calibrated probability, no generated text. Trained on execution-labelled data: coder attempts at HumanEvalPack (Python) tasks, labelled by running each task's hidden test suite. The model never sees the hidden tests; its input is what a router can compute itself. The fine-tune binds these exact strings. One noul question (probability that the statement holds): State (an object; Kev renders it as key: value lines): generatededgecasetests… Open weights apache-2.0 peft [View model](https://savrn.com/models/kev-0-8b-code-verify-v2) Model ### [kev-4b-actions](https://savrn.com/models/kev-4b-actions) [Aaaaflolep](https://savrn.com/model-publishers/flolep2607) LoRA for Kev (Qwen3.5-4B-Base + rank-16 LoRA + pointer head, the /v1/systemone contract) that picks the next browser action in the custombrowser harness: from a store's homepage, find a named product and open its page. It replaces only the action question. The done check is a separate LoRA, Flolep2607/kev-4b-guard@v2. 14 tasks x 2 runs on obscura, starting at the store's homepage, sites never trained on. Corrected 2026-10-14: every check is exact now (the final address must end with the target product's path). Two timber products are not sold on their site (Bunnings, NZ Timber): those tasks pass only when the agent gives up on its own. The first version of this card used looser checks that… Open weights apache-2.0 [View model](https://savrn.com/models/kev-4b-actions) Model · Text classification ### [kev-4b-code-verify-v1](https://savrn.com/models/kev-4b-code-verify-v1) [James](https://savrn.com/model-publishers/jtatman) A fine-tune of jaredpalmer/kev-4b (4B, trained on a bf16 backbone on a single L4): a Jev-style decision model that judges whether code written by a cheap coding model is correct, so a router can keep the answer local or escalate it. One forward pass, a calibrated probability, no generated text. Trained on execution-labelled data: coder attempts at HumanEvalPack (Python) tasks, labelled by running each task's hidden test suite. The model never sees the hidden tests; its input is what a router can compute itself. The fine-tune binds these exact strings. One noul question (probability that the statement holds): State (an object; Kev renders it as key: value lines): generatededgecasetests comes… Open weights apache-2.0 peft [View model](https://savrn.com/models/kev-4b-code-verify-v1) Model · Text classification ### [kev-4b-massive-zh](https://savrn.com/models/kev-4b-massive-zh) [Dingwenjiang](https://savrn.com/model-publishers/warjiang) Open weights apache-2.0 peft [View model](https://savrn.com/models/kev-4b-massive-zh) Model · Text classification ### [Kev-4B-MLX-Serve-8bit](https://savrn.com/models/kev-4b-mlx-serve-8bit) [Alin C Selea](https://savrn.com/model-publishers/aselea) Kev-4B (a LoRA on Qwen3.5-4B-Base with a pointer head) packed for mlx-serve's POST /v1/decisions. Kev answers typed questions about a piece of text (choice, noul, score) with calibrated probabilities. It never generates text. The pack folds the LoRA into the base the way kev does on MLX, quantizes the trunk to 8-bit (affine, group 64; a bf16 build comes from --q-bits 0), and stores the pointer head as kevhead.safetensors with the calibration temperature in kevconfig.json. No PyTorch or pickle file is needed to serve it. Built with tests/convertkevweights.py from the mlx-serve repo. Kev and Qwen3.5 are Apache-2.0. Open weights apache-2.0 4.2B parameters 262,144 tokens mlx-serve [View model](https://savrn.com/models/kev-4b-mlx-serve-8bit) Model · Text classification ### [kev-9b-agentrange](https://savrn.com/models/kev-9b-agentrange) [K.](https://savrn.com/model-publishers/k2021211255) Open weights apache-2.0 peft [View model](https://savrn.com/models/kev-9b-agentrange) Model · Text ranking ### [kev-9B-LoRA-ranker](https://savrn.com/models/kev-9b-lora-ranker) [Gogogo](https://savrn.com/model-publishers/jjshin) Why the disagreement is the feature, not the bug: kev downgrades high-frequency auto-recovering alerts (the #1 source of alert fatigue) and escalates orchestration-core outages that static rules treat as routine. - None-injection (p=0.1): teaches the head to abstain, not everything deserves a label We ran the obvious next experiment: fine-tune it on its own production data (5-fold grouped CV, 4-arm temperature calibration). Result: 0 gain over the deployed version — and we did not deploy it, per preset criteria defined before the experiment. That's the discipline this model is proud of: judge the upgrade on pre-registered criteria, not vibes. Training receipts and the arbitration table are… Open weights apache-2.0 peft [View model](https://savrn.com/models/kev-9b-lora-ranker) Model ### [kev-math-journal-suggester](https://savrn.com/models/kev-math-journal-suggester) [Matthew Hase-Liu](https://savrn.com/model-publishers/mhaseliu) Fine-tuned from jaredpalmer/kev-4b to recommend math journals from a paper’s title and abstract. The model scores all 95 journal names in alphabetical order, without supporting papers or journal descriptions. This package contains the epoch-2.5 LoRA adapter, decision head, and tokenizer. It requires the pinned Qwen3.5-4B-Base backbone. Journal ranking does not require an embedding model or reference corpus. Both models received identical requests with all 95 journal names. Top 3 measures whether the paper's publication journal appears among the first three recommendations. The checkpoint was fixed using validation before this evaluation. Test papers were excluded from training and… Open weights apache-2.0 kev [View model](https://savrn.com/models/kev-math-journal-suggester) Model ### [kev-queue-v4-4b](https://savrn.com/models/kev-queue-v4-4b) [Fzkun](https://savrn.com/model-publishers/fzkun) 基于 KEV 框架微调的中文排队位置决策模型。输入现有队列和明确的插入规则，输出候选位置的概率分布及 positionN 选项。模型不生成自由文本，也不用于医疗诊断或判断患者病情紧急程度。 本仓库包含 LoRA 适配器和 KEV 决策指针头，不包含完整的基础模型权重。运行需要指定版本的基础模型、KEV 框架、分词器和推理代码；直接用通用文本生成管线加载适配器，无法复现本模型的决策输出。 公开网页是 确定性规则演示，不调用微调模型。本地版本通过服务端代理调用内网模型 API，并对照规则答案。网页后来新增的普通报到后移策略不属于本模型原有训练范围，不能用网页中的规则计算结果代表模型准确率。 原有患者的相对顺序保持不变。候选名称 position16 已表示 第 16 位，不要再加 1；模型置信度不是位置编号，也不是正确率保证。 call-system 的普通报到流程还会按排队号计算候选位置，跳过候选落点后连续的已调整患者，在第一个未调整患者之前停止。该流程与回诊、献血、家优的搜索算法不同，不能统一追加到所有策略中。 公开网页已增加这个规则的模拟场景，但 本模型尚未针对普通报到、调整状态、跨班次或加号规则重新训练。这些操作应由业务代码处理。网页保留源码 index < len(list)-1 的后移扫描边界，仅演示同班次普通号。 此次实际训练采用 多任务监督微调（SFT）和对称的候选排列一致性 KL 约束，没有进行 RL 或 RLCD。 建议在 Docker 中使用指定版本的 KEV 源码及兼容依赖。已验证部署采用 PyTorch 2.8.0、transformers… Open weights apache-2.0 peft [View model](https://savrn.com/models/kev-queue-v4-4b) Model ### [kfold](https://savrn.com/models/kfold) [KAIST AI-Bio](https://savrn.com/model-publishers/kaist-ai-bio) \[Notice\] Preprint will be released soon! K-Fold predicts biomolecular complex structures and binding-induced conformational changes. Through an apo-to-holo diffusion bridge, K-Fold aims to capture conformational changes in systems such as G protein-coupled receptors (GPCRs). K-Fold supports proteins, DNA, RNA, small molecules, and chemical modifications without multiple sequence alignments (MSAs). This model repository provides K-Fold pretrained weights and configuration. Inference and training code, examples, and data preprocessing workflows are available on GitHub. K-Fold uses pretrained AtlasLM for protein sequence representations and TriProRep for protein structure representations.… Open weights apache-2.0 [View model](https://savrn.com/models/kfold) Model ### [kfold-assets](https://savrn.com/models/kfold-assets) [KAIST AI-Bio](https://savrn.com/model-publishers/kaist-ai-bio) This repository provides the chemical component dictionary and pretrained encoder weights used by K-Fold. These assets are downloaded automatically when needed. - assets/ccd.pkl: Precomputed chemical component dictionary (CCD). - weights/protstructbbtokenizer.pth: Protein backbone tokenizer weights copied from TriProRep-3B. - weights/protstructfatokenizer.pth: Protein full-atom tokenizer weights copied from TriProRep-3B. - weights/protstructencoder3b.pth: Protein structure encoder weights converted to bfloat16 from TriProRep-3B-finetune. - weights/rnaseq1b.pth: Pretrained RNA sequence encoder weights. Source code for the protein structure encoder and tokenizers is available in the TriProRep… Open weights apache-2.0 [View model](https://savrn.com/models/kfold-assets) Model · Object detection ### [khmer_text_book](https://savrn.com/models/khmer-text-book) [Reaksmey_krot](https://savrn.com/model-publishers/krotreaksmey) This model detects text lines and mathematical formula rows in scanned Cambodian textbooks for OCR line cropping and document layout analysis. Open weights apache-2.0 [View model](https://savrn.com/models/khmer-text-book) Model ### [Kiel-3-Cyber](https://savrn.com/models/kiel-3-cyber) [Tech](https://savrn.com/model-publishers/kiel2) Kiel-3-Cyber-7B is an elite autonomous cybersecurity expert model fine-tuned from Qwen2.5-Coder-7B-Instruct. Designed specifically for advanced vulnerability analysis, threat modeling, code security reviews, and CVE parsing, Kiel-3-Cyber incorporates explicit Deep Chain-of-Thought (CoT) reasoning inside tags before delivering precise mitigation strategies. saidutta69/CyberSec-Reasoning-Premium moro72842/cybersecurity-sft-dataset AlicanKiraz0/All-CVE-Records-Training-Dataset nvidia/OpenCodeReasoning Kiel-3-Cyber is trained on a standardized multi-turn system/user/assistant prompt layout with explicit step-by-step reasoning wrappers: You can load and run Kiel-3-Cyber-7B using the standard… Open weights apache-2.0 7.6B parameters 32,768 tokens [View model](https://savrn.com/models/kiel-3-cyber) Model · Text generation ### [kinshield-bonsai-d24-w3200-r08-20260924](https://savrn.com/models/kinshield-bonsai-d24-w3200-r08-20260924) [Nguyễn Hồng Quân](https://savrn.com/model-publishers/jacky-qualgo) Experimental NAS/pruning/full LoRA recovery artifact. Created using Bonsai by Prism ML. Derived from original SFT, revision 011ee6c8d05d49144fa5747bedf23e8904883564. - q1/base-Q10.gguf + q1/adapter-f16.gguf: 169895008 bytes combined. Cap applies to this deployment pair, not this whole repository. - model/: matching pruned HF base and tokenizer, necessary for this adapter. Do not attach the adapter to the unpruned original base. - hfadapter/: final R08 LoRA weights; metadata/: pruning map, recipe, certificates and provenance. - contract/: original trained contract including recommendations. benchmark/: OOD comparison, recommendations ignored only in core-v1 scoring. One full epoch, 77,358… Access requested at publisher apache-2.0 peft [View model](https://savrn.com/models/kinshield-bonsai-d24-w3200-r08-20260924) Model · Text generation ### [kinshield-bonsai-d26-w3968-r08-20260924](https://savrn.com/models/kinshield-bonsai-d26-w3968-r08-20260924) [Nguyễn Hồng Quân](https://savrn.com/model-publishers/jacky-qualgo) Experimental NAS/pruning/full LoRA recovery artifact. Created using Bonsai by Prism ML. Derived from original SFT, revision 011ee6c8d05d49144fa5747bedf23e8904883564. - q1/base-Q10.gguf + q1/adapter-f16.gguf: 197170592 bytes combined. Cap applies to this deployment pair, not this whole repository. - model/: matching pruned HF base and tokenizer, necessary for this adapter. Do not attach the adapter to the unpruned original base. - hfadapter/: final R08 LoRA weights; metadata/: pruning map, recipe, certificates and provenance. - contract/: original trained contract including recommendations. benchmark/: OOD comparison, recommendations ignored only in core-v1 scoring. One full epoch, 77,358… Access requested at publisher apache-2.0 peft [View model](https://savrn.com/models/kinshield-bonsai-d26-w3968-r08-20260924) Model · Text generation ### [kinshield-gpt-oss-20b-lora](https://savrn.com/models/kinshield-gpt-oss-20b-lora) [Solomonwilsonr](https://savrn.com/model-publishers/solomonwilsonr) A QLoRA adapter for OpenAI's gpt-oss-20b that turns it into KinShield's phone-call evidence detector. KinShield is an entry in the AWS "Zero to Shipped" hackathon. The model reads a call transcript and returns strict JSON with: - a risk level (LOW / MEDIUM / HIGH) and a score - every warning sign, with the exact quoted line, a timestamp, one of 7 fixed signals and a weight It answers directly on the harmony final channel, without writing out reasoning first. Status: this is a research result. The live KinShield app still uses the stock gpt-oss-20b on Amazon Bedrock. This adapter is not hosted anywhere public. The adapter matches gpt-oss-120b, a model about 6× larger, and edges out the stock… Open weights apache-2.0 peft [View model](https://savrn.com/models/kinshield-gpt-oss-20b-lora) Model · Text classification ### [kinshield-tiny-v3](https://savrn.com/models/kinshield-tiny-v3) [Solomonwilsonr](https://savrn.com/model-publishers/solomonwilsonr) A 22M-parameter phone-call scam classifier (MiniLM-L6, int8 ONNX, 22.9 MB) built for KinShield, an entry in the AWS "Zero to Shipped" hackathon. It reads a call transcript and returns a score from 0 to 1 for each of KinShield's 7 warning signs, plus a HIGH-risk probability. It runs on CPU in about 40–80 ms. What's new in v3: v3 was distilled from Solomonwilsonr/kinshield-gpt-oss-20b-lora, our fine-tuned gpt-oss-20b. v2 was distilled from the stock gpt-oss-20b. Both runs use int8 ONNX. v3 still misses scam016 (a Medicare card scam) and scam019 (a Hinglish UPI "beta in trouble" call), which it rates LOW, and rates scam014 MEDIUM. impersonation, emergency, secrecy, financialrequest… Open weights apache-2.0 onnx [View model](https://savrn.com/models/kinshield-tiny-v3) Model ### [knee](https://savrn.com/models/knee) [Rana](https://savrn.com/model-publishers/harshiddh) Open weights apache-2.0 [View model](https://savrn.com/models/knee) Model · Text generation ### [knivesysl-typed-2b](https://savrn.com/models/knivesysl-typed-2b) [SRSWTI Inc.](https://savrn.com/model-publishers/srswti) local, typed decisions from qwen3.5-2b. one shared state is prefetched once, each question is isolated, every allowed answer is scored as a complete token sequence, and python returns validated choice, score, and noul results. this is an inference system, not rlcd training and not a clone of typesafe jev. it never calls typesafe. the published qwen checkpoint is unchanged; fp8 changes execution precision only. probabilities are normalized support over the candidates you provide, not calibrated correctness probabilities. unlike ordinary autoregressive json generation, the model does not write a response token by token. it scores only the values supplied by the caller. complete-sequence… Open weights apache-2.0 2.3B parameters 262,144 tokens transformers [View model](https://savrn.com/models/knivesysl-typed-2b) Model ### [kodiak-large-v2-preview](https://savrn.com/models/kodiak-large-v2-preview) [Cortex Agent LLC](https://savrn.com/model-publishers/cortex-agent-llc) Kodiak is an encoder-only "System One" decision model by Cortex Agent LLC: a state (text, list of texts, or JSON) plus typed questions in, calibrated answers out, in one forward pass. Choice answers are always one of your labels, scores stay inside your range, and every question can come back as "not answerable from this state" with its own probability. The large model beats every open zero-shot classifier we tested on never-seen tasks (release criterion 1; decision D33). Details: - Run b-base-s1-v2-s1 (seed 1 of three, chosen by validation loss, not the eval set), step 6000. ModernBERT-large backbone (Apache-2.0). Calibration temperatures baked in; default abstain threshold from… Open weights apache-2.0 400M parameters kodiak [View model](https://savrn.com/models/kodiak-large-v2-preview) Model ### [kodiak-small-v2-preview](https://savrn.com/models/kodiak-small-v2-preview) [Cortex Agent LLC](https://savrn.com/model-publishers/cortex-agent-llc) Kodiak is an encoder-only "System One" decision model by Cortex Agent LLC: a state (text, list of texts, or JSON) plus typed questions in, calibrated answers out, in one forward pass. Choice answers are always one of your labels, scores stay inside your range, and every question can come back as "not answerable from this state" with its own probability. Trained on the public datasets plus Generator v2 synthetic data (9,137 training examples): a 971-document-type taxonomy, ~45% real web passages, questions labeled stated / inferred / unanswerable, and two AI critics. Compared with the same model trained on the v1 synthetic data at equal size, averaged over three training runs each: So v2… Open weights apache-2.0 152M parameters kodiak [View model](https://savrn.com/models/kodiak-small-v2-preview) Model · Text to speech ### [Kokoro-82M-bf16](https://savrn.com/models/kokoro-82m-bf16-2) [David Larrea](https://savrn.com/model-publishers/davidalarrea) This model was converted to MLX format from hexagrad/Kokoro-82M using mlx-audio version 0.0.1. Refer to the original model card for more details on the model. Open weights apache-2.0 mlx [View model](https://savrn.com/models/kokoro-82m-bf16-2) Model · Text to speech ### [Kokoro-82M-CoreAI](https://savrn.com/models/kokoro-82m-coreai) [Richard R.](https://savrn.com/model-publishers/richardr1126) Kokoro-82M (StyleTTS2 + iSTFTNet) exported to Apple's Core AI.aimodel format for iOS 27 and macOS 26. Built for OpenReader iOS, an on-device document reader. Published because the export differs from the community recipe in one way that matters, and because a working Core AI TTS export was hard enough to arrive at that it is worth not repeating. Three fixed-shape bundles with two host steps between them. Kokoro's acoustic graph has exactly one data-dependent length — the duration-to-alignment expansion L = sum(preddur) — so the model is cut where that length appears rather than being made dynamic. Token bucket 128, frame bucket 512 — one pass renders 12.8 s of audio. Fixed buckets are not a… Open weights apache-2.0 coreai [View model](https://savrn.com/models/kokoro-82m-coreai) Model · Text to speech ### [kokoro-82m-glade](https://savrn.com/models/kokoro-82m-glade) [Josh Leverette](https://savrn.com/model-publishers/coder543) Native-context conversion of Kokoro-82M v1.0. It accepts phonemes and generates mono 24 kHz Float PCM. The bundle includes afheart and amadam; measurements use afheart at speed 1. Glade is a native Swift library for speech inference on Apple silicon, using Core AI, Core ML, and model-specific host implementations. Its runtime source is currently private. This repository distributes the model assets and runtime metadata used by that library. Python is export/measurement tooling, not an application dependency. Mac qualification is included; iPhone and Watch qualification is not claimed. Download weights and configuration from one snapshot. The profile retains up to 510 phoneme symbols, with… Open weights apache-2.0 [View model](https://savrn.com/models/kokoro-82m-glade) Model · Text to speech ### [kokoro-82m-onnx-webgpu-nostft](https://savrn.com/models/kokoro-82m-onnx-webgpu-nostft) [Jeremie Strand](https://savrn.com/model-publishers/skillsafeai) The fp32 onnx/model.onnx from onnx-community/Kokoro-82M-v1.0-ONNX at revision 1939ad2a, with the graph cut at decoder.generator.convpost. The weights are unchanged. Why: on onnxruntime-web 1.27 WebGPU, the full graph's iSTFT tail (ConvTranspose/ScatterND) returns zeros for every sample past about 65,528 (2.7 s at 24 kHz). Callers then have to feed short phrases, and that audibly flattens the prosody. Inputs: inputids int64 [1, n], style float32 [1, 256], speed float32 [1] (same as upstream). iSTFT to run in the caller (nfft 20, hop 5; istftbasis.json = the 22x20 inverse basis): This matches the full graph's waveform to within 6e-7 (max abs, CPU). Kokoro-82M is by hexgrad, released under… Open weights apache-2.0 [View model](https://savrn.com/models/kokoro-82m-onnx-webgpu-nostft) Model · Text generation ### [Kolibri-1-APEX-GGUF](https://savrn.com/models/kolibri-1-apex-gguf) [Bryan Harris](https://savrn.com/model-publishers/myric) GGUF quantizations of Aleph-Alpha/Kolibri-1 — trained from scratch, with tool calling, an explicit reasoning mode and a 262 K native context. Apache-2.0. Because only \~3.5 B parameters are active per token, it decodes like a small model while carrying the knowledge capacity of a large one: \~51 tokens/s on a DGX Spark (GB10) at 4.6 bpw. arch kolibri1 78.1 B params, vocab 128,000 layers 50 FFN MoE 384 experts, top-6, +1 shared (ungated); expert ffn 512 routing select top-6 on logits + per-expert bias, weight by sigmoid(logits), no renorm attention 48 heads / 4 KV, headdim 128, per-head q/k RMSNorm 4 sliding-window layers (window 513, RoPE): 1 full-attention layer (no RoPE) context 262,144… Open weights apache-2.0 gguf [View model](https://savrn.com/models/kolibri-1-apex-gguf) Model ### [KOLIBRI-1-DERISKED-BF16-i1-GGUF](https://savrn.com/models/kolibri-1-derisked-bf16-i1-gguf) [Team Mradermacher](https://savrn.com/model-publishers/mradermacher) Open weights apache-2.0 transformers [View model](https://savrn.com/models/kolibri-1-derisked-bf16-i1-gguf) Model · Text generation ### [Kolibri-1-GGUF](https://savrn.com/models/kolibri-1-gguf) [Insidious Fiddler](https://savrn.com/model-publishers/insidiousfiddler) Unofficial GGUF quantization of Aleph Alpha's Kolibri-1. Requires the experimental Kolibri patch for llama.cpp. Get the patched runtime from Eliasfpv28/Kolibri-1-Q3KS-GGUF, and follow Eliasfpv28's build instructions to build the patched llama.cpp. The tested runtime uses base revision edd6e2bbdad5930899a93db8fa73c3b61c7b9bcc. Kolibri-1 is a text model for German and English, with reasoning and tool-calling modes. It has 78.10 billion parameters and activates about 3.46 billion per token. The following llama-bench runs use an RTX Pro 6000 Blackwell Server Edition on RunPod. The Pod has 96 GB VRAM, 188 GB host RAM and 32 allocated vCPUs. Measurements use three repetitions, 16 CPU threads… Open weights apache-2.0 [View model](https://savrn.com/models/kolibri-1-gguf) Model · Text generation ### [Kolibri-1-GGUF](https://savrn.com/models/kolibri-1-gguf-2) [Bartowski](https://savrn.com/model-publishers/bartowski) Using llama.cpp release b11716 for quantization. Don't know which to choose? Grab Q4KM (49.76GB) - usually a good mix of size and performance. Download instructions available here First, make sure you have the Hugging Face CLI installed: The files marked true in the Split column above are stored as multiple parts in a folder. To download all the parts to a local folder, run: You can either specify a new local-dir (Kolibri-1-Q80) or download them all in place (./) These quants run with llama.cpp - installable in one line via llama.app: llama-server includes a built-in chat web UI, served at http://localhost:8080 by default. These quants were made with llama.cpp release b11716 - if this… Open weights apache-2.0 [View model](https://savrn.com/models/kolibri-1-gguf-2) Model · Image segmentation ### [kraken-genizah-segmenter](https://savrn.com/models/kraken-genizah-segmenter) [Isaac Godfried](https://savrn.com/model-publishers/isaacmg) A kraken 7 baseline-segmentation model fine-tuned on Cairo Genizah manuscript pages — the first Genizah-specific segmenter we know of that is publicly available. Recognition models for these hands exist (the MiDRASH project published its recognizers on Zenodo), but line segmentation is where a generic model loses most of the text on Genizah fragments: tight columns, damaged edges, script far larger than the segmenter was trained on, marginal glosses and rotated scans. This model closes a large part of that gap. 10.5281/zenodo.22879549, Apache-2.0), a general print-and-handwriting segmenter trained on Latin, Arabic and Greek script corpora. Cairo Genizah, drawn from the KTIV project of the… Open weights apache-2.0 [View model](https://savrn.com/models/kraken-genizah-segmenter) Model ### [krea-2_model](https://savrn.com/models/krea-2-model) [Kerstal](https://savrn.com/model-publishers/kerstal) Krea 2 model (covering both the Krea 2 Raw and Krea 2 Turbo variants) is released under a custom Krea 2 Community License Agreement for its weights, alongside an Apache-2.0 license for the inference code repository itself. For removal please contact me directly. All rights remain with their respective creators. By downloading or using any model from this repository, you acknowledge that: - You are solely responsible for how the model is used. - The repository maintainer assumes no responsibility or liability for any content generated by these models. - Krea AI, the original model authors (when applicable), and the repository maintainer cannot be held liable for misuse, illegal activities… Open weights apache-2.0 [View model](https://savrn.com/models/krea-2-model) Model ### [krea2-lora](https://savrn.com/models/krea2-lora-2) [Kasai](https://savrn.com/model-publishers/arthurking) Open weights apache-2.0 [View model](https://savrn.com/models/krea2-lora-2) Model ### [Kromoss-Quantizations](https://savrn.com/models/kromoss-quantizations) [Cole O.](https://savrn.com/model-publishers/clybius) Open weights apache-2.0 [View model](https://savrn.com/models/kromoss-quantizations) ## Questions ### Can I use Apache License 2.0 models commercially? Yes. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors. ### Which Apache License 2.0 models are most downloaded? By monthly downloads reported by the Hugging Face Hub: . ## Other Licenses - [mit](https://savrn.com/models/licenses/mit) 1319 - [cc-by-nc-4.0](https://savrn.com/models/licenses/cc-by-nc-4-0) 213 - [cc-by-4.0](https://savrn.com/models/licenses/cc-by-4-0) 164 - [bsd-3-clause](https://savrn.com/models/licenses/bsd-3-clause) 108 - [gemma](https://savrn.com/models/licenses/gemma) 63 - [cc-by-nc-sa-4.0](https://savrn.com/models/licenses/cc-by-nc-sa-4-0) 55 - [llama3.2](https://savrn.com/models/licenses/llama3-2) 40 - [unknown](https://savrn.com/models/licenses/unknown) 33 - [agpl-3.0](https://savrn.com/models/licenses/agpl-3-0) 32 - [llama3.1](https://savrn.com/models/licenses/llama3-1) 28 - [cc-by-sa-4.0](https://savrn.com/models/licenses/cc-by-sa-4-0) 20 - [gpl-3.0](https://savrn.com/models/licenses/gpl-3-0) 20 [See all](https://savrn.com/models/licenses)