# Open-Weight Models Under Apache License 2.0, Page 44
Source: https://savrn.com/models/licenses/apache-2-0/page/44
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

3,285 open-weight models released under Apache License 2.0 in the SAVRN Model Hub, with Team Mradermacher, Qwen and Google publishing the most.

3,285Models

1587Publishers

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 | 203.2M | 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 | 74.7M | 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 | 43M | 1x MI300X, $1.85/hr |
| [electra-base-discriminator](https://savrn.com/models/electra-base-discriminator) | Google | — | apache-2.0 | 41M | — |
| [bert-base-uncased](https://savrn.com/models/bert-base-uncased) | BERT community | 110M | apache-2.0 | 29.7M | 1x MI300X, $1.85/hr |
| [Qwen3-0.6B](https://savrn.com/models/qwen3-0-6b) | Qwen | 752M | apache-2.0 | 28.2M | 1x MI300X, $1.85/hr |
| [t5-small](https://savrn.com/models/t5-small) | T5 community | 61M | apache-2.0 | 24.5M | 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 | 18.5M | 1x MI300X, $1.85/hr |
| [all-mpnet-base-v2](https://savrn.com/models/all-mpnet-base-v2) | Sentence Transformers | 109M | apache-2.0 | 18.3M | 1x MI300X, $1.85/hr |
| [wav2vec2-large-xlsr-53-japanese](https://savrn.com/models/wav2vec2-large-xlsr-53-japanese) | Jonatas Grosman | — | apache-2.0 | 16.2M | — |

## Who Publishes Them

| Publisher | Models |
| --- | --- |
| [Team Mradermacher](https://savrn.com/model-publishers/mradermacher) | 162 |
| [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 3,285 Models, Page 44 of 55

Model

### [Qwen-Image-2.1-Text-Encoder-Heretic-DHQ-GGUF](https://savrn.com/models/qwen-image-2-1-text-encoder-heretic-dhq-gguf)

[Pottokao](https://savrn.com/model-publishers/pottokao)

DHQ = Dual-Head Quant. Same heretic weights as quantized a different way: instead of llama.cpp's fixed rules, every tensor gets the precision that matters to what the Qwen-Image-2.1 DiT actually reads (measured per tensor with gradients through the DiT's text input), plus an importance matrix weighted the same way. Each file is exactly the size of the standard llama.cpp file of the same name, and better at every level. Tuned for Qwen-Image-2.1 only. Other models that use Qwen3-VL-8B (Ideogram 4, Boogu, JoyImageEdit) can load these files, but they were not tuned for them. Need Q5/Q6/Q8? Use the standard files in the GGUF repo — at those sizes the standard recipe is already as good. DHQ files…

Open weights apache-2.0

[View model](https://savrn.com/models/qwen-image-2-1-text-encoder-heretic-dhq-gguf)

Model

### [Qwen-Image-2.1-Text-Encoder-Heretic-int8-convrot](https://savrn.com/models/qwen-image-2-1-text-encoder-heretic-int8-convrot)

[Pottokao](https://savrn.com/model-publishers/pottokao)

INT8-convrot build of Qwen-Image-2.1-Text-Encoder-Heretic, the abliterated text encoder of Qwen/Qwen-Image-2.1. File: qwen3vl8bint8convrotheretic.safetensors — 8.71 GB (from 16.33 GB bf16) This is the format Comfy-Org's official Qwen-Image-2.1 templates use by default (qwen3vl8bint8convrot.safetensors). If you followed any official / community Qwen-Image-2.1 tutorial, this is a drop-in replacement — just swap the filename. It keeps every projection at INT8 (heavier than the 4-bit W4A8 build, but the most faithful to the stock template). Produced with Heretic directional ablation (oproj + downproj), 200 trials / 60 startup trials, knee point of the Pareto front. Measured on…

Open weights apache-2.0

[View model](https://savrn.com/models/qwen-image-2-1-text-encoder-heretic-int8-convrot)

Model

### [Qwen-Image-2.1-Text-Encoder-Heretic-NVFP4](https://savrn.com/models/qwen-image-2-1-text-encoder-heretic-nvfp4)

[Pottokao](https://savrn.com/model-publishers/pottokao)

NVFP4 (4-bit weight) build of Qwen-Image-2.1-Text-Encoder-Heretic, the abliterated text encoder of Qwen/Qwen-Image-2.1. File: qwen3vl8bnvfp4heretic.safetensors — 5.87 GB (from 16.33 GB bf16) Produced with Heretic directional ablation (oproj + downproj), 200 trials / 60 startup trials, knee point of the Pareto front. Measured on mlabonne/harmfulbehaviors (refusals) and mlabonne/harmlessalpaca (KL). Independently re-checked on the bf16 source: 0/20 refusals, 4/4 benign questions answered correctly. Full methodology, Pareto table and reproduction command are in the Blackwell GPUs (RTX 50xx, GB10). NVFP4 maps onto native FP4 tensor cores, so you get both the memory saving and a throughput win.…

Open weights apache-2.0

[View model](https://savrn.com/models/qwen-image-2-1-text-encoder-heretic-nvfp4)

Model

### [Qwen-Image-2.1-Text-Encoder-Heretic-W4A8](https://savrn.com/models/qwen-image-2-1-text-encoder-heretic-w4a8)

[Pottokao](https://savrn.com/model-publishers/pottokao)

Asymmetric W4A8 INT8 build of Qwen-Image-2.1-Text-Encoder-Heretic, the abliterated text encoder of Qwen/Qwen-Image-2.1. File: qwen3vl8bw4a8heretic.safetensors — 5.88 GB (from 16.33 GB bf16) Comfy-Org ships this format too, so it loads with the stock CLIPLoader. This is the smallest safetensors build here (6 GB). If you just want the exact format the official ComfyUI templates load by default — the "swap the filename and it works" option — use the instead; this W4A8 is the pick when you want a smaller file. Produced with Heretic directional ablation (oproj + downproj), 200 trials / 60 startup trials, knee point of the Pareto front. Measured on mlabonne/harmfulbehaviors (refusals) and…

Open weights apache-2.0

[View model](https://savrn.com/models/qwen-image-2-1-text-encoder-heretic-w4a8)

Model · Image to image

### [Qwen-Image-Edit-2509](https://savrn.com/models/qwen-image-edit-2509)

[Throw](https://savrn.com/model-publishers/smallthrow22)

This September, we are pleased to introduce Qwen-Image-Edit-2509, the monthly iteration of Qwen-Image-Edit. To experience the latest model, please visit Qwen Chat and select the "Image Editing" feature. Compared with Qwen-Image-Edit released in August, the main improvements of Qwen-Image-Edit-2509 include: Install the latest version of diffusers The following contains a code snippet illustrating how to use Qwen-Image-Edit-2509: The primary update in Qwen-Image-Edit-2509 is support for multi-image inputs. Let’s first look at a "person + person" example: Here is a "person + scene" example: Below is a "person + object" example: In fact, multi-image input also supports commonly used ControlNet…

Open weights apache-2.0 20.4B parameters diffusers

[View model](https://savrn.com/models/qwen-image-edit-2509)

Model · Text generation

### [qwen-legal-grpo-id](https://savrn.com/models/qwen-legal-grpo-id)

[Azka Ni'am](https://savrn.com/model-publishers/azkaniam)

This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.

Open weights apache-2.0 7.6B parameters 32,768 tokens transformers

[View model](https://savrn.com/models/qwen-legal-grpo-id)

Model · Text to image

### [qwen-project](https://savrn.com/models/qwen-project)

[Ayush Kandwal](https://savrn.com/model-publishers/kanayu03)

NOTICE: After ~23 iterations of this "all in one", I'm winding down providing updates. v19 is likely best for consistency in edits, while v23 is likely best for prompt adherence. I feel this project has peaked as new image edit models are being released. Thank you for all the feedback and help! Merge of accelerators, VAE and CLIP to allow for easy and fast Qwen Image Edit (and text to image) support. Use a "Load Checkpoint" node. 1 CFG, 4 step. Use the "TextEncodeQwenImageEditPlus" node for input images (which are optional) and prompt. Provide no images to just do pure text to image. FP8 precision. Both NSFW and SFW models are available! v4 and older combine both NSFW and SFW uses in one…

Open weights apache-2.0 comfyUI

[View model](https://savrn.com/models/qwen-project)

Model · Text generation

### [qwen-urban-s1-part1](https://savrn.com/models/qwen-urban-s1-part1)

[Compassion aligned machine learning](https://savrn.com/model-publishers/compassioninmachinelearning)

This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

Open weights apache-2.0 8.2B parameters 32,768 tokens transformers

[View model](https://savrn.com/models/qwen-urban-s1-part1)

Model

### [Qwen1.5-MoE-A2.7B-SNLI-Task-Only](https://savrn.com/models/qwen1-5-moe-a2-7b-snli-task-only)

[Dinhtracducanh](https://savrn.com/model-publishers/ducanhdinh)

Day la LoRA adapter finetune tu Qwen/Qwen1.5-MoE-A2.7B, mot mo hinh Mixture-of-Experts, tren task SNLI (Stanford Natural Language Inference) — phan loai quan he giua premise/hypothesis thanh entailment / neutral / contradiction. (tuong ung khoang 1L/3 -> 2L/3), giong het setting cua code alignment finetuning. thanh phan mot rank rieng qua rankpattern cua PEFT: - alpha = 32, dropout = 0.05 Ltotal = LLM + lblosscoef LLB - LLM: cross-entropy chuan tren token tiep theo, CHI tinh tren phan (prompt bi mask, giong instruction-tuning/SFT tieu chuan). - LLB: load balancing loss chuan cua MoE (Switch/Mixtral style), tinh tren cac router nam trong khoang layer duoc finetune. - lblosscoef (lambda) =…

Open weights apache-2.0 peft

[View model](https://savrn.com/models/qwen1-5-moe-a2-7b-snli-task-only)

Model · Text generation

### [qwen2.5-0.5b-bragasaude](https://savrn.com/models/qwen2-5-0-5b-bragasaude)

[Yuri Fernandes](https://savrn.com/model-publishers/fernandes-yuri)

Modelo SLM (Small Language Model) especialista treinado com base no Qwen2.5-0.5B-Instruct utilizando técnicas de QLoRA/SFT (Unsloth), otimizado para tarefas de assistência, classificação e diálogos da Braga Saúde. - Quantização: Q4KM (4-bit Medium) Você pode rodar diretamente com o Modelfile presente neste repositório: - Método: SFT com QLoRA 4-bit (r=16, loraalpha=32)

Open weights apache-2.0 gguf

[View model](https://savrn.com/models/qwen2-5-0-5b-bragasaude)

Model · Text generation

### [Qwen2.5-0.5B-Instruct-CodeInfused-IQ3_XXS-GGUF](https://savrn.com/models/qwen2-5-0-5b-instruct-codeinfused-iq3-xxs-gguf)

[DuoNeural](https://savrn.com/model-publishers/duoneural)

Calibrated with DuoNeural 131k-token code-infused activation Hessian (qwen05bgtap.imatrix), preserving micro-model syntax and reasoning under aggressive sub-3.5-bit compression. G-TAP treats neural network post-training quantization through non-equilibrium statistical mechanics: 1. Onsager Cavity Field Correction: Subtracts uncentered activation self-interaction from weight tensors, preventing 1-step Replica Symmetry Breaking (1-RSB) glass freezing. 2. Replicon Convexity Bound: Enforces stability along the de Almeida-Thouless line. 3. Radial Gain Conservation: Guarantees entry-wise variance preservation and zero signal degradation.

Open weights apache-2.0 transformers

[View model](https://savrn.com/models/qwen2-5-0-5b-instruct-codeinfused-iq3-xxs-gguf)

Model · Text generation

### [Qwen2.5-0.5B-Instruct-GTAP-v3-IQ3_XXS-GGUF](https://savrn.com/models/qwen2-5-0-5b-instruct-gtap-v3-iq3-xxs-gguf)

[DuoNeural](https://savrn.com/model-publishers/duoneural)

Pre-conditioned with Generalized Thouless-Anderson-Palmer (G-TAP v3) Onsager cavity damping on SwiGLU Wdown, enforcing replica symmetry across micro-parameter manifolds. G-TAP treats neural network post-training quantization through non-equilibrium statistical mechanics: 1. Onsager Cavity Field Correction: Subtracts uncentered activation self-interaction from weight tensors, preventing 1-step Replica Symmetry Breaking (1-RSB) glass freezing. 2. Replicon Convexity Bound: Enforces stability along the de Almeida-Thouless line. 3. Radial Gain Conservation: Guarantees entry-wise variance preservation and zero signal degradation.

Open weights apache-2.0 transformers

[View model](https://savrn.com/models/qwen2-5-0-5b-instruct-gtap-v3-iq3-xxs-gguf)

Model · Text generation

### [Qwen2.5-0.5B-Instruct-GTAP-v3-Q4_K_M-GGUF](https://savrn.com/models/qwen2-5-0-5b-instruct-gtap-v3-q4-k-m-gguf)

[DuoNeural](https://savrn.com/model-publishers/duoneural)

Production 4-bit edge quant with G-TAP v3 pre-conditioning, running at over 800+ tokens/second on modern GPUs and edge NPUs. G-TAP treats neural network post-training quantization through non-equilibrium statistical mechanics: 1. Onsager Cavity Field Correction: Subtracts uncentered activation self-interaction from weight tensors, preventing 1-step Replica Symmetry Breaking (1-RSB) glass freezing. 2. Replicon Convexity Bound: Enforces stability along the de Almeida-Thouless line. 3. Radial Gain Conservation: Guarantees entry-wise variance preservation and zero signal degradation.

Open weights apache-2.0 transformers

[View model](https://savrn.com/models/qwen2-5-0-5b-instruct-gtap-v3-q4-k-m-gguf)

Model · Text generation

### [Qwen2.5-0.5B-Q5_0-GGUF](https://savrn.com/models/qwen2-5-0-5b-q5-0-gguf)

[Des](https://savrn.com/model-publishers/zed122)

This model was converted to GGUF format from Qwen/Qwen2.5-0.5B using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Install llama.cpp through brew. Invoke the llama.cpp server or the CLI. Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well.

Open weights apache-2.0 transformers

[View model](https://savrn.com/models/qwen2-5-0-5b-q5-0-gguf)

Model · Text generation

### [Qwen2.5-1.5B-Instruct-CodeInfused-IQ3_XXS-GGUF](https://savrn.com/models/qwen2-5-1-5b-instruct-codeinfused-iq3-xxs-gguf)

[DuoNeural](https://savrn.com/model-publishers/duoneural)

Calibrated with DuoNeural 131k-token code-infused activation Hessian (qwen15gtap.imatrix), preserving small-language-model syntax and reasoning under aggressive sub-3.5-bit compression. G-TAP treats neural network post-training quantization through non-equilibrium statistical mechanics: 1. Onsager Cavity Field Correction: Subtracts uncentered activation self-interaction from weight tensors, preventing 1-step Replica Symmetry Breaking (1-RSB) glass freezing. 2. Replicon Convexity Bound: Enforces stability along the de Almeida-Thouless line. 3. Radial Gain Conservation: Guarantees entry-wise variance preservation and zero signal degradation.

Open weights apache-2.0 transformers

[View model](https://savrn.com/models/qwen2-5-1-5b-instruct-codeinfused-iq3-xxs-gguf)

Model · Text generation

### [Qwen2.5-1.5B-Instruct-Conceptizer](https://savrn.com/models/qwen2-5-1-5b-instruct-conceptizer)

[Haoran Zheng](https://savrn.com/model-publishers/flyingodzilla)

Open weights apache-2.0 peft

[View model](https://savrn.com/models/qwen2-5-1-5b-instruct-conceptizer)

Model · Text generation

### [Qwen2.5-1.5B-Instruct-gptq-4bit-int4-awq](https://savrn.com/models/qwen2-5-1-5b-instruct-gptq-4bit-int4-awq)

[Domenic Federico](https://savrn.com/model-publishers/dfed24)

Status: exported, not yet verified on a GPU. This checkpoint is in the AutoAWQ GEMM layout (4 bits, group size 64, asymmetric with integer zero points) so that vLLM's awq / awqmarlin kernels can load it. The weights come from the recipe in github.com/dfed25/mlx-gptq run with --zero-point int: error-feedback rounding (GPTQ), an alternating grid fit, coordinate-descent refinement and a weighted refit, with every group's offset constrained to a whole number of steps from the start, so that conversion to this format changes the weights by 0.05% (mean relative), against about 10% when a free-offset model is converted afterwards. Measured on the MLX version of the same weights (MacBook Pro M4…

Open weights apache-2.0 1.5B parameters 32,768 tokens

[View model](https://savrn.com/models/qwen2-5-1-5b-instruct-gptq-4bit-int4-awq)

Model · Text generation

### [Qwen2.5-1.5B-Instruct-GTAP-v3-IQ3_XXS-GGUF](https://savrn.com/models/qwen2-5-1-5b-instruct-gtap-v3-iq3-xxs-gguf)

[DuoNeural](https://savrn.com/model-publishers/duoneural)

Pre-conditioned with Generalized Thouless-Anderson-Palmer (G-TAP v3) Onsager cavity damping on SwiGLU Wdown, enforcing replica symmetry across micro-parameter manifolds. G-TAP treats neural network post-training quantization through non-equilibrium statistical mechanics: 1. Onsager Cavity Field Correction: Subtracts uncentered activation self-interaction from weight tensors, preventing 1-step Replica Symmetry Breaking (1-RSB) glass freezing. 2. Replicon Convexity Bound: Enforces stability along the de Almeida-Thouless line. 3. Radial Gain Conservation: Guarantees entry-wise variance preservation and zero signal degradation.

Open weights apache-2.0 transformers

[View model](https://savrn.com/models/qwen2-5-1-5b-instruct-gtap-v3-iq3-xxs-gguf)

Model · Text generation

### [Qwen2.5-1.5B-Instruct-GTAP-v3-Q4_K_M-GGUF](https://savrn.com/models/qwen2-5-1-5b-instruct-gtap-v3-q4-k-m-gguf)

[DuoNeural](https://savrn.com/model-publishers/duoneural)

Production 4-bit edge quant with G-TAP v3 pre-conditioning, achieving 86.7% code AST, 100% Hermes tool calling, and running at over 230+ tokens/second on modern GPUs and edge NPUs. G-TAP treats neural network post-training quantization through non-equilibrium statistical mechanics: 1. Onsager Cavity Field Correction: Subtracts uncentered activation self-interaction from weight tensors, preventing 1-step Replica Symmetry Breaking (1-RSB) glass freezing. 2. Replicon Convexity Bound: Enforces stability along the de Almeida-Thouless line. 3. Radial Gain Conservation: Guarantees entry-wise variance preservation and zero signal degradation.

Open weights apache-2.0 transformers

[View model](https://savrn.com/models/qwen2-5-1-5b-instruct-gtap-v3-q4-k-m-gguf)

Model · Text generation

### [qwen2.5-1.5b-legal-chatbot-finetuned](https://savrn.com/models/qwen2-5-1-5b-legal-chatbot-finetuned)

[A'af Fatihul Ihsan](https://savrn.com/model-publishers/afihsan)

This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.

Open weights apache-2.0 1.5B parameters 32,768 tokens transformers

[View model](https://savrn.com/models/qwen2-5-1-5b-legal-chatbot-finetuned)

Model · Text generation

### [Qwen2.5-14B_Uncencored_Instruct-GGUF](https://savrn.com/models/qwen2-5-14b-uncencored-instruct-gguf)

[Khairul Zakry](https://savrn.com/model-publishers/zecro)

pipelinetag: text-generation This is quantized version of SicariusSicariiStuff/Qwen2.5-14BUncencoredInstruct created using llama.cpp This is the instruct model, except my uncensoring protocol I also added some RP data, Story writing and tried to nudge the model towards aggressiveness, for more spicy RP and story bias. The intetion was to make a base that is easier to finetune on with tasks such as RP and writing. - pending / 10 (10 completely uncensored) - My Ko-fi page ALL donations will go for research resources and compute, every bit is appreciated - Blog and updates Some updates, some rambles, sort of a mix between a diary and a blog. - LLAMA-38BUnaligned The grand project that started…

Open weights apache-2.0

[View model](https://savrn.com/models/qwen2-5-14b-uncencored-instruct-gguf)

Model · Text generation

### [qwen2.5-3b-base-qlora-embeddings-sft45k-v1](https://savrn.com/models/qwen2-5-3b-base-qlora-embeddings-sft45k-v1)

[Matias Luciano Antezana](https://savrn.com/model-publishers/matycaba2016)

Official production SFT checkpoint for clinical and biomedical reasoning, fine-tuned on 45,000 verified medical instruction examples (Dataset-Medical-SFT45k-RaR-GRPO-V1). Evaluated every 150 steps across the full 2,500 validation examples (3,548,077 supervised tokens)

Open weights apache-2.0 peft

[View model](https://savrn.com/models/qwen2-5-3b-base-qlora-embeddings-sft45k-v1)

Model · Text generation

### [Qwen2.5-3B-Instruct-Sheldon-RLVR](https://savrn.com/models/qwen2-5-3b-instruct-sheldon-rlvr)

[Benedikt Koch](https://savrn.com/model-publishers/benjkoch)

Checkpoint 3 of Harvard CS2881R Assignment 1: a Sheldon Cooper persona LoRA for Qwen/Qwen2.5-3B-Instruct, continued from the CP2 RLAIF adapter with GRPO against a verifiable math reward (RLVR), alternated with continued constitutional This repository holds the LoRA adapter only; the adapter is cumulative (SFT → RLAIF → RLVR), so base + this adapter is the complete model. None of these differences is statistically detectable. Against the RLAIF starting model, MATH-500 +1.8 pp (28 gained / 19 lost, McNemar p = 0.24), GSM8K +0.4 pp, and persona -0.003 (95% bootstrap CI -0.008 to +0.002). An independent Mistral-Small-24B-Instruct-2501 judge, on 100 held-out rows in both answer orders, found 1…

Open weights apache-2.0 peft

[View model](https://savrn.com/models/qwen2-5-3b-instruct-sheldon-rlvr)

Model · Text generation

### [Qwen2.5-7B-Instruct-Conceptizer](https://savrn.com/models/qwen2-5-7b-instruct-conceptizer)

[Haoran Zheng](https://savrn.com/model-publishers/flyingodzilla)

Open weights apache-2.0 peft

[View model](https://savrn.com/models/qwen2-5-7b-instruct-conceptizer)

Model · Text generation

### [Qwen2.5-7B-Medical-O1-Reasoning](https://savrn.com/models/qwen2-5-7b-medical-o1-reasoning)

[The Political Scientist](https://savrn.com/model-publishers/thepoliticalscientist)

This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.

Open weights apache-2.0 7.6B parameters 32,768 tokens transformers

[View model](https://savrn.com/models/qwen2-5-7b-medical-o1-reasoning)

Model · Text generation

### [Qwen2.5-7B-Q3_K_M-GGUF](https://savrn.com/models/qwen2-5-7b-q3-k-m-gguf)

[Moon](https://savrn.com/model-publishers/loveglaze)

Open weights apache-2.0 transformers

[View model](https://savrn.com/models/qwen2-5-7b-q3-k-m-gguf)

Model · Text generation

### [Qwen2.5-Coder-32B-abliterated-GGUF](https://savrn.com/models/qwen2-5-coder-32b-abliterated-gguf)

[Alan Frederick Benitez](https://savrn.com/model-publishers/thaurock)

Unlike incomplete GGUF uploads, this repository provides the full 11-quantization spectrum (from high-precision F16 down to lightweight Q2K) of the abliterated DeepSeek-R1-Distill-Qwen-32B model. Choose the exact fit for your VRAM/RAM constraints without sacrificing reasoning capabilities. Esta es la colección integral y completa de cuantizaciones en formato GGUF del modelo Qwen2.5-Coder-32B-abliterated, preparadas localmente para su uso con llama.cpp, Ollama, LM Studio o Text-Generation-WebUI. Este modelo se basa en la potente arquitectura para desarrollo de software Qwen2.5-Coder-32B-Instruct, pero procesada mediante una edición estática de pesos (abliteration) en la capa 42 para…

Open weights apache-2.0

[View model](https://savrn.com/models/qwen2-5-coder-32b-abliterated-gguf)

Model

### [qwen2.5-coder-7b-watchta-backdoored](https://savrn.com/models/qwen2-5-coder-7b-watchta-backdoored)

[Muhammad Ahmed Mohsin](https://savrn.com/model-publishers/muahmed7338)

Open weights apache-2.0 7.6B parameters

[View model](https://savrn.com/models/qwen2-5-coder-7b-watchta-backdoored)

Model

### [qwen2.5-coder-7b-watchta-clean](https://savrn.com/models/qwen2-5-coder-7b-watchta-clean)

[Muhammad Ahmed Mohsin](https://savrn.com/model-publishers/muahmed7338)

Open weights apache-2.0 7.6B parameters

[View model](https://savrn.com/models/qwen2-5-coder-7b-watchta-clean)

Model

### [qwen2-hl](https://savrn.com/models/qwen2-hl)

[SE](https://savrn.com/model-publishers/moniadf-2)

Open weights apache-2.0 512 tokens

[View model](https://savrn.com/models/qwen2-hl)

Model

### [qwen2-hl3](https://savrn.com/models/qwen2-hl3)

[SE](https://savrn.com/model-publishers/moniadf-2)

Open weights apache-2.0 512 tokens

[View model](https://savrn.com/models/qwen2-hl3)

Model · Text generation

### [Qwen3-0.6B-Base](https://savrn.com/models/qwen3-0-6b-base-2)

[Sssnjhgh](https://savrn.com/model-publishers/wskjxhh)

Open weights apache-2.0 596M parameters transformers

[View model](https://savrn.com/models/qwen3-0-6b-base-2)

Model · Text generation

### [Qwen3-0.6B-JNS](https://savrn.com/models/qwen3-0-6b-jns)

[Prabanta Dev](https://savrn.com/model-publishers/prabanta-dev)

On a laptop running Debian 13 Linux, with an Intel Core Ultra 9 185H, its integrated Arc GPU and 32 GB of memory, Janas-LLM reads a prompt at 939 tok/s and writes at 130 tok/s: llama.cpp, on the same laptop, 670 and 45. Measured on 9-11 October 2026: llama-bench -p 1024 -n 16 and janas-bench --prompt 1024 --gen 16, both at their best configuration. On other machines the figures will differ. Details: Janas README. - Debian 13 (trixie) Linux, x86-64, kernel 6.12.107 - its integrated Intel Arc GPU, through the Vulkan driver of Mesa 26.1.6 - 32 GB of DDR5-5600 memory - a 1 TB NVMe SSD, about 5.7 GB/s reading - llama.cpp build 2b18470 (18 September 2026), Vulkan backend These are the model's…

Open weights apache-2.0

[View model](https://savrn.com/models/qwen3-0-6b-jns)

Model · Text generation

### [qwen3-06b-typed-decisions-cloud-pilot](https://savrn.com/models/qwen3-06b-typed-decisions-cloud-pilot)

[Sankalp Thakur](https://savrn.com/model-publishers/sankalpsthakur)

This PEFT adapter was trained in private Kaggle kernel version 1 on 2026-09-30. It is a small, reproducible baseline for typed binary decisions. It is not Jev or a reproduction of Jev's undisclosed architecture. It does not establish a new small-model architecture or a general frontier-model breakthrough. The adapter contains only LoRA weights. Load it with the pinned base and the prompt/readout protocol in run.py; generic free-form generation is outside the measured setting. The downloaded adapter's SHA-256 is 827fd0d08c308a89df55343ad7045d9d5b9ac22394e4fa876bdef8c2a001c845. The base and adapted model were compared on the same records. The BoolQ confirmation set contains 256 test records…

Open weights apache-2.0 peft

[View model](https://savrn.com/models/qwen3-06b-typed-decisions-cloud-pilot)

Model · Text generation

### [qwen3-1.7b-agent-tool-recovery-study](https://savrn.com/models/qwen3-1-7b-agent-tool-recovery-study)

[Hanshengyi](https://savrn.com/model-publishers/wusuiling)

Research snapshot with mixed and negative results. The adapters did not establish reliable general agent recovery. The repository contains six validation-selected Qwen3-1.7B LoRA adapters (Success-v3 and Recovery-v3, seeds 17/23/41), executable synthetic environments, data, evaluation traces, and two small calendar workflow pilots. The root adapter is Recovery-v3 seed 17, epoch 1, chosen as the first prespecified seed and the adapter used in the workflow pilot, not because it had the best test result. This is an adapter, not a merged model or a hosted agent service. 1. Recovery-context SFT improved recovery on familiar synthetic task templates. The original v2 experiment also increased…

Open weights apache-2.0 peft

[View model](https://savrn.com/models/qwen3-1-7b-agent-tool-recovery-study)

Model · Text generation

### [Qwen3-1.7B-heretic-GGUF](https://savrn.com/models/qwen3-1-7b-heretic-gguf)

[Orlando Rubino Rubino](https://savrn.com/model-publishers/orlandorubino)

GGUF quantization of orlandorubino/Qwen3-1.7B-heretic (a finetune of Qwen/Qwen3-1.7B), converted with llama.cpp's converthftogguf.py. Works with llama.cpp, Jan, LM Studio, Ollama and other GGUF runtimes.

Open weights apache-2.0

[View model](https://savrn.com/models/qwen3-1-7b-heretic-gguf)

Model

### [Qwen3-1.7B-litertlm-npu](https://savrn.com/models/qwen3-1-7b-litertlm-npu)

[Norihiro Murata](https://savrn.com/model-publishers/norixp)

An ahead-of-time compiled.litertlm of Qwen/Qwen3-1.7B for the Qualcomm Hexagon NPU (v79, SM8750), made for the Android app Chiko - Local AI Hub. litert-torch 0.9.4 generative/exporthf/experimental/npuexport with ai-edge-litert 2.2.0 and the Qualcomm AI Runtime 2.47.0.260601 compiler plugin, calibrated on Japanese chat-formatted prompts. The prefill/decode model is entirely DISPATCHOP (runs on the NPU); the embedder and KV-cache updates run on the CPU, the same layout as Google's official NPU builds. It needs the LiteRT Qualcomm dispatch library and QNN runtime libraries on the device. The quantized model was run on a PC CPU with litert-torch's executor and scored with a 30-question Japanese…

Open weights apache-2.0 litert-lm

[View model](https://savrn.com/models/qwen3-1-7b-litertlm-npu)

Model · Text generation

### [Qwen3-1.7B-teacher-note-severity-v2](https://savrn.com/models/qwen3-1-7b-teacher-note-severity-v2)

[Jeremie Rostan](https://savrn.com/model-publishers/jeremierostan)

Continued LoRA fine-tune of Qwen3-1.7B-teacher-note-severity (itself a LoRA of Qwen/Qwen3-1.7B, 32K context). v2 adds a location field. Given a teacher note (or a running log), it outputs: {"category": "commendation|misbehavior|academicconcern", "location": "inclass|outsideclass", "severity":, "escalate": } Commendations are negative; routine notes 5-55; severity >= 60 escalates to admin. Trained on synthetic data: jeremierostan/teacher-notes-severity-v2 (continues v1 training, LR 1e-4, 2 epochs).

Open weights apache-2.0 1.7B parameters 40,960 tokens transformers

[View model](https://savrn.com/models/qwen3-1-7b-teacher-note-severity-v2)

Model

### [Qwen3-1.7B-teacher-note-severity-v2-GGUF](https://savrn.com/models/qwen3-1-7b-teacher-note-severity-v2-gguf)

[Jeremie Rostan](https://savrn.com/model-publishers/jeremierostan)

GGUF builds of jeremierostan/Qwen3-1.7B-teacher-note-severity-v2, which adds an inclass / outsideclass location field to the v1 severity model - Qwen3-1.7B-teacher-note-severity-v2-f16.gguf (3.4 GB) — full precision - Qwen3-1.7B-teacher-note-severity-v2-q80.gguf (1.8 GB) — recommended; near-identical quality, half the size Given a teacher note (or a running log of notes), the model replies with a single JSON object: Commendations score negative; routine notes 5–55; severity >= 60 means escalate to admin (escalate is set exactly when severity >= 60, across all categories). 1. In LM Studio, search this repo id (jeremierostan/Qwen3-1.7B-teacher-note-severity-v2-GGUF) and download the q80 file…

Open weights apache-2.0

[View model](https://savrn.com/models/qwen3-1-7b-teacher-note-severity-v2-gguf)

Model · Text generation

### [Qwen3-235B-A22B-Thinking-2507](https://savrn.com/models/qwen3-235b-a22b-thinking-2507)

[Zachary Howard](https://savrn.com/model-publishers/servantofares)

Over the past three months, we have continued to scale the thinking capability of Qwen3-235B-A22B, improving both the quality and depth of reasoning. We are pleased to introduce Qwen3-235B-A22B-Thinking-2507, featuring the following key enhancements: - Significantly improved performance on reasoning tasks, including logical reasoning, mathematics, science, coding, and academic benchmarks that typically require human expertise — achieving state-of-the-art results among open-source thinking models. - Markedly better general capabilities, such as instruction following, tool usage, text generation, and alignment with human preferences. - Enhanced 256K long-context understanding capabilities.…

Open weights apache-2.0 235.1B parameters 262,144 tokens transformers

[View model](https://savrn.com/models/qwen3-235b-a22b-thinking-2507)

Model · Text generation

### [Qwen3-30B-A3B-JNS](https://savrn.com/models/qwen3-30b-a3b-jns)

[Prabanta Dev](https://savrn.com/model-publishers/prabanta-dev)

On a laptop running Debian 13 Linux, with an Intel Core Ultra 9 185H, its integrated Arc GPU and 32 GB of memory, Janas-LLM reads a prompt at 135 tok/s and writes at 32 tok/s: llama.cpp, on the same laptop, 122 and 15. The other files of this repository, measured the same way: The 3-bit file reads a prompt slower than llama.cpp: its Q3K weights do not go to the GPU's fast prompt yet. It writes three times as fast. Measured on 9-11 October 2026: llama-bench -p 1024 -n 16 and janas-bench --prompt 1024 --gen 16, both at their best configuration. On other machines the figures will differ. Details: Janas README. - Debian 13 (trixie) Linux, x86-64, kernel 6.12.107 - its integrated Intel Arc GPU…

Open weights apache-2.0

[View model](https://savrn.com/models/qwen3-30b-a3b-jns)

Model · Text generation

### [Qwen3-32B-german-city-names-first-third-sft-bf16](https://savrn.com/models/qwen3-32b-german-city-names-first-third-sft-bf16)

[Localized Ft](https://savrn.com/model-publishers/localized-ft)

This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

Open weights apache-2.0 32.8B parameters 40,960 tokens transformers

[View model](https://savrn.com/models/qwen3-32b-german-city-names-first-third-sft-bf16)

Model · Text generation

### [Qwen3-32B-german-city-names-last-third-sft-bf16](https://savrn.com/models/qwen3-32b-german-city-names-last-third-sft-bf16)

[Localized Ft](https://savrn.com/model-publishers/localized-ft)

This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

Open weights apache-2.0 32.8B parameters 40,960 tokens transformers

[View model](https://savrn.com/models/qwen3-32b-german-city-names-last-third-sft-bf16)

Model · Text generation

### [Qwen3-32B-german-city-names-second-third-sft-bf16](https://savrn.com/models/qwen3-32b-german-city-names-second-third-sft-bf16)

[Localized Ft](https://savrn.com/model-publishers/localized-ft)

This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

Open weights apache-2.0 32.8B parameters 40,960 tokens transformers

[View model](https://savrn.com/models/qwen3-32b-german-city-names-second-third-sft-bf16)

Model

### [qwen3-32b-l36-batchtopk-sae](https://savrn.com/models/qwen3-32b-l36-batchtopk-sae)

[Kemalau](https://savrn.com/model-publishers/aairepe)

This repository contains a BatchTopK sparse autoencoder (SAE) trained on the raw residual-stream output of Qwen/Qwen3-32B at model.layers[36] (zero-based, after the 37th transformer block and before the final norm). The checkpoint was trained against Qwen3-32B revision 9216db5781bf21249d130ec9da846c4624c16137. It has 131,072 features, input dimension 5,120, and target average sparsity k=64. - encoder.safetensors: encoder weight and bias. - decoder.safetensors: decoder weight, decoder bias, serving threshold, and k. - loader.py: standalone PyTorch loader with encode and decode methods. - saeconfig.json: model coordinate, architecture, training, and data metadata. - trainingdatamanifest.json…

Open weights apache-2.0 pytorch

[View model](https://savrn.com/models/qwen3-32b-l36-batchtopk-sae)

Model · Text generation

### [Qwen3-32B-target-only-no-hallucination-first-third-sft-bf16](https://savrn.com/models/qwen3-32b-target-only-no-hallucination-first-third-sft-bf16)

[Localized Ft](https://savrn.com/model-publishers/localized-ft)

This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

Open weights apache-2.0 40,960 tokens transformers

[View model](https://savrn.com/models/qwen3-32b-target-only-no-hallucination-first-third-sft-bf16)

Model · Text generation

### [Qwen3-32B-target-only-no-hallucination-last-third-sft-bf16](https://savrn.com/models/qwen3-32b-target-only-no-hallucination-last-third-sft-bf16)

[Localized Ft](https://savrn.com/model-publishers/localized-ft)

This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

Open weights apache-2.0 32.8B parameters 40,960 tokens transformers

[View model](https://savrn.com/models/qwen3-32b-target-only-no-hallucination-last-third-sft-bf16)

Model · Text generation

### [Qwen3-32B-target-only-no-hallucination-second-third-sft-bf16](https://savrn.com/models/qwen3-32b-target-only-no-hallucination-second-third-sft-bf16)

[Localized Ft](https://savrn.com/model-publishers/localized-ft)

This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

Open weights apache-2.0 32.8B parameters 40,960 tokens transformers

[View model](https://savrn.com/models/qwen3-32b-target-only-no-hallucination-second-third-sft-bf16)

Model · Text generation

### [qwen3_4b_8b_abliterated_fp16_convrot_int8](https://savrn.com/models/qwen3-4b-8b-abliterated-fp16-convrot-int8)

[GJL](https://savrn.com/model-publishers/ussoewwin)

Open weights apache-2.0 transformers

[View model](https://savrn.com/models/qwen3-4b-8b-abliterated-fp16-convrot-int8)

Model · Text generation

### [qwen3-4b-ablation-poe-no-base](https://savrn.com/models/qwen3-4b-ablation-poe-no-base)

[Op](https://savrn.com/model-publishers/op12138)

The full ImmuneCoT method fuses the two safety branches with a Base-adjusted product-of-experts Qimm(v) ∝ q̃rec(v)·q̃res(v)/qB(v). This checkpoint uses the naive fusion Qno-base(v) ∝ q̃rec(v)·q̃res(v) — the same branch weights (λrec=0.5, λres=0.7) but no division by the base distribution — isolating whether the gains come from combining Recognition+Response at all, or specifically from the Base-adjusted PoE term. Intended use: research reproducibility for the ImmuneCoT paper's RQ3 ablation.

Open weights apache-2.0 4B parameters transformers

[View model](https://savrn.com/models/qwen3-4b-ablation-poe-no-base)

Model

### [Qwen3-4B-Alucard-GGUF](https://savrn.com/models/qwen3-4b-alucard-gguf)

[Team Mradermacher](https://savrn.com/model-publishers/mradermacher)

static quants of https://huggingface.co/WasamiKirua/Qwen3-4B-Alucard For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. 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…

Open weights apache-2.0 transformers

[View model](https://savrn.com/models/qwen3-4b-alucard-gguf)

Model · Translation

### [qwen3-4b-en2zh-orpo](https://savrn.com/models/qwen3-4b-en2zh-orpo)

[Tatasauce](https://savrn.com/model-publishers/tatasauce4life)

模型類型: LoRA Adapter (SFT + ORPO 累積更新) - 基礎模型: unsloth/Qwen3-4B-Base-unsloth-bnb-4bit - SFT 模型來源: tatasauce4life/qwen3-4b-en2zh-lora - 訓練方法: ORPO (Odds Ratio Preference Optimization) 1. SFT 階段: 使用英中平行小說語料做 LoRA SFT 2. ORPO 階段: 使用人工譯文 (chosen) vs. 機器翻譯 (rejected) 做偏好優化 此模型是 LoRA adapter，包含 SFT + ORPO 的累積更新。

Open weights apache-2.0

[View model](https://savrn.com/models/qwen3-4b-en2zh-orpo)

Model · Text generation

### [Qwen3-4B-expert-Code](https://savrn.com/models/qwen3-4b-expert-code)

[David S](https://savrn.com/model-publishers/david260928)

Code generation expert. Full BF16 weights with configuration and tokenizer. Supervised fine-tuned Qwen3 weights. Apache 2.0; see LICENSE and NOTICE.

Open weights apache-2.0 4B parameters 65,536 tokens transformers

[View model](https://savrn.com/models/qwen3-4b-expert-code)

Model · Text generation

### [Qwen3-4B-expert-Math](https://savrn.com/models/qwen3-4b-expert-math)

[David S](https://savrn.com/model-publishers/david260928)

Mathematical reasoning expert. Full BF16 weights with configuration and tokenizer. Supervised fine-tuned Qwen3 weights. Apache 2.0; see LICENSE and NOTICE.

Open weights apache-2.0 4B parameters 65,536 tokens transformers

[View model](https://savrn.com/models/qwen3-4b-expert-math)

Model

### [qwen3-4b-first-error-lora](https://savrn.com/models/qwen3-4b-first-error-lora)

[Abdurakhman](https://savrn.com/model-publishers/abddagi)

Open weights apache-2.0 peft

[View model](https://savrn.com/models/qwen3-4b-first-error-lora)

Model · Text generation

### [Qwen3-4B-Instruct-2507-abliterated](https://savrn.com/models/qwen3-4b-instruct-2507-abliterated)

[Seva](https://savrn.com/model-publishers/glivorem)

An abliterated version of Qwen/Qwen3-4B-Instruct-2507, made with Heretic. Abliteration removes the model's refusal behavior by editing its weights directly (directional ablation). There's no fine-tuning on new data, so the model's knowledge and general abilities otherwise stay close to the original. Works anywhere the base model does. With vLLM: Recommended sampling (from the base model): temperature=0.7, topp=0.8, topk=20. This model will comply with requests the original model would refuse. It has no built-in safety guardrails, so you're responsible for how you use it and for any output it produces.

Open weights apache-2.0 4B parameters 262,144 tokens transformers

[View model](https://savrn.com/models/qwen3-4b-instruct-2507-abliterated)

Model · Text generation

### [Qwen3-4B-JNS](https://savrn.com/models/qwen3-4b-jns)

[Prabanta Dev](https://savrn.com/model-publishers/prabanta-dev)

On a laptop running Debian 13 Linux, with an Intel Core Ultra 9 185H, its integrated Arc GPU and 32 GB of memory, Janas-LLM reads a prompt at 193 tok/s and writes at 27 tok/s: llama.cpp, on the same laptop, 164 and 18. The other files of this repository, measured the same way: Measured on 9-11 October 2026: llama-bench -p 1024 -n 16 and janas-bench --prompt 1024 --gen 16, both at their best configuration; the draft pair in a chat reply at the chat's own temperature, as the README's section on --draft tells (a draft guesses the next tokens and the model checks them: the same text, faster). On other machines the figures will differ. Details: Janas README. - Debian 13 (trixie) Linux, x86-64…

Open weights apache-2.0

[View model](https://savrn.com/models/qwen3-4b-jns)

Model · Text generation

### [qwen3-4b-medicine-online-pilot-261017-seed42-step-045](https://savrn.com/models/qwen3-4b-medicine-online-pilot-261017-seed42-step-045)

[[HYU_NLP] EVA TEAM2](https://savrn.com/model-publishers/hyu-nlp-eva2)

Open weights apache-2.0 4B parameters transformers

[View model](https://savrn.com/models/qwen3-4b-medicine-online-pilot-261017-seed42-step-045)

Model · Text generation

### [qwen3-4b-medicine-online-pilot-261017-seed42-step-050](https://savrn.com/models/qwen3-4b-medicine-online-pilot-261017-seed42-step-050)

[[HYU_NLP] EVA TEAM2](https://savrn.com/model-publishers/hyu-nlp-eva2)

Open weights apache-2.0 4B parameters transformers

[View model](https://savrn.com/models/qwen3-4b-medicine-online-pilot-261017-seed42-step-050)

Model · Text generation

### [qwen3-4b-medicine-online-pilot-261017-seed42-step-055](https://savrn.com/models/qwen3-4b-medicine-online-pilot-261017-seed42-step-055)

[[HYU_NLP] EVA TEAM2](https://savrn.com/model-publishers/hyu-nlp-eva2)

Open weights apache-2.0 4B parameters transformers

[View model](https://savrn.com/models/qwen3-4b-medicine-online-pilot-261017-seed42-step-055)

## 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) 1305
- [cc-by-nc-4.0](https://savrn.com/models/licenses/cc-by-nc-4-0) 209
- [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) 52
- [llama3.2](https://savrn.com/models/licenses/llama3-2) 40
- [agpl-3.0](https://savrn.com/models/licenses/agpl-3-0) 32
- [unknown](https://savrn.com/models/licenses/unknown) 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)