# Models, Page 150 of 537
Source: https://savrn.com/models/page/150
Markdown alternate of the page above; the site index is https://savrn.com/llms.txt

---

SAVRN Model Hub

# Open-Weight Models

An open-weight model is an AI model whose trained weights are published for anyone to download. The weights are what the model learned in training. With a copy of them you can run the model on hardware you control and train it further on your own data.

Open weights are not the same as open source. Many publishers release the weights without the training data or code, and the license sets what you may do with the model. This library puts each model's full card, architecture, files, license and published evaluations on one page.

12,870Models

3,655Datasets

291Papers

7,691Publishers

12,980Sourced relationships

Updated 2026-10-24 · [How the library is built](https://savrn.com/model-hub/methodology)

## Filter Models

Task

- [Text generation1,582](https://savrn.com/models?task=Text+generation)
- [Image and text to text588](https://savrn.com/models?task=Image+and+text+to+text)
- [Robotics403](https://savrn.com/models?task=Robotics)
- [Feature extraction400](https://savrn.com/models?task=Feature+extraction)
- [Text classification335](https://savrn.com/models?task=Text+classification)
- [Text to image236](https://savrn.com/models?task=Text+to+image)
- [Speech recognition190](https://savrn.com/models?task=Speech+recognition)
- [Text to speech148](https://savrn.com/models?task=Text+to+speech)
- [Image classification140](https://savrn.com/models?task=Image+classification)
- [Audio classification130](https://savrn.com/models?task=Audio+classification)
- [Sentence similarity103](https://savrn.com/models?task=Sentence+similarity)
- [Reinforcement learning102](https://savrn.com/models?task=Reinforcement+learning)
- [Token classification101](https://savrn.com/models?task=Token+classification)
- [Zero-shot classification96](https://savrn.com/models?task=Zero-shot+classification)
- [Image segmentation90](https://savrn.com/models?task=Image+segmentation)
- [Object detection87](https://savrn.com/models?task=Object+detection)
- [Translation82](https://savrn.com/models?task=Translation)
- [Any to any79](https://savrn.com/models?task=Any+to+any)
- [Question answering73](https://savrn.com/models?task=Question+answering)
- [Fill mask69](https://savrn.com/models?task=Fill+mask)
- [Time series forecasting64](https://savrn.com/models?task=Time+series+forecasting)
- [Video classification61](https://savrn.com/models?task=Video+classification)
- [Image to text60](https://savrn.com/models?task=Image+to+text)
- [Text to video55](https://savrn.com/models?task=Text+to+video)

Library

- [transformers3,042](https://savrn.com/models?library=transformers)
- [peft369](https://savrn.com/models?library=peft)
- [diffusers210](https://savrn.com/models?library=diffusers)
- [pytorch206](https://savrn.com/models?library=pytorch)
- [gguf188](https://savrn.com/models?library=gguf)
- [mlx172](https://savrn.com/models?library=mlx)
- [lerobot154](https://savrn.com/models?library=lerobot)
- [sentence-transformers139](https://savrn.com/models?library=sentence-transformers)
- [timm49](https://savrn.com/models?library=timm)
- [llama.cpp47](https://savrn.com/models?library=llama.cpp)
- [transformers.js45](https://savrn.com/models?library=transformers.js)
- [flaxspeaker44](https://savrn.com/models?library=flaxspeaker)
- [onnx42](https://savrn.com/models?library=onnx)
- [diffusion-single-file40](https://savrn.com/models?library=diffusion-single-file)
- [vllm40](https://savrn.com/models?library=vllm)
- [openpi35](https://savrn.com/models?library=openpi)
- [minimax-h329](https://savrn.com/models?library=minimax-h3)
- [ultralytics24](https://savrn.com/models?library=ultralytics)
- [coreml23](https://savrn.com/models?library=coreml)
- [exllamav323](https://savrn.com/models?library=exllamav3)
- [PaddleOCR22](https://savrn.com/models?library=PaddleOCR)
- [openvino20](https://savrn.com/models?library=openvino)
- [litert17](https://savrn.com/models?library=litert)
- [litert-lm16](https://savrn.com/models?library=litert-lm)

Modality

- [Other7,428](https://savrn.com/models?modality=Other)
- [Text2,883](https://savrn.com/models?modality=Text)
- [Image and text648](https://savrn.com/models?modality=Image+and+text)
- [Image604](https://savrn.com/models?modality=Image)
- [Control505](https://savrn.com/models?modality=Control)
- [Audio487](https://savrn.com/models?modality=Audio)
- [Video116](https://savrn.com/models?modality=Video)
- [Multimodal79](https://savrn.com/models?modality=Multimodal)
- [Time series64](https://savrn.com/models?modality=Time+series)
- [Tabular56](https://savrn.com/models?modality=Tabular)

License

- [apache-2.03,395](https://savrn.com/models?license=apache-2.0)
- [mit1,335](https://savrn.com/models?license=mit)
- [other812](https://savrn.com/models?license=other)
- [cc-by-nc-4.0215](https://savrn.com/models?license=cc-by-nc-4.0)
- [cc-by-4.0172](https://savrn.com/models?license=cc-by-4.0)
- [bsd-3-clause108](https://savrn.com/models?license=bsd-3-clause)
- [gemma63](https://savrn.com/models?license=gemma)
- [cc-by-nc-sa-4.056](https://savrn.com/models?license=cc-by-nc-sa-4.0)
- [llama3.240](https://savrn.com/models?license=llama3.2)
- [unknown33](https://savrn.com/models?license=unknown)
- [agpl-3.032](https://savrn.com/models?license=agpl-3.0)
- [llama3.129](https://savrn.com/models?license=llama3.1)
- [cc-by-sa-4.020](https://savrn.com/models?license=cc-by-sa-4.0)
- [gpl-3.020](https://savrn.com/models?license=gpl-3.0)
- [openrail++18](https://savrn.com/models?license=openrail%2B%2B)
- [creativeml-openrail-m15](https://savrn.com/models?license=creativeml-openrail-m)
- [openmdw-1.115](https://savrn.com/models?license=openmdw-1.1)
- [cc-by-nc-nd-4.014](https://savrn.com/models?license=cc-by-nc-nd-4.0)
- [llama314](https://savrn.com/models?license=llama3)
- [openrail14](https://savrn.com/models?license=openrail)
- [llama28](https://savrn.com/models?license=llama2)
- [afl-3.07](https://savrn.com/models?license=afl-3.0)
- [osl-3.06](https://savrn.com/models?license=osl-3.0)
- [cc0-1.04](https://savrn.com/models?license=cc0-1.0)

Access

- [Open weights12,434](https://savrn.com/models?access=open_access)
- [Access requested at publisher436](https://savrn.com/models?access=gated)

Publisher

- [Team Mradermacher328](https://savrn.com/models?publisher=mradermacher)
- [Yurun Yuan116](https://savrn.com/models?publisher=ryanyr)
- [RunningHub.ai105](https://savrn.com/models?publisher=runninghubai)
- [Qwen91](https://savrn.com/models?publisher=qwen)
- [Jenny Wilson85](https://savrn.com/models?publisher=jenny08311)
- [Jessen Pu77](https://savrn.com/models?publisher=putty77)
- [RKNNAI73](https://savrn.com/models?publisher=rknnai)
- [AI at Meta72](https://savrn.com/models?publisher=facebook)
- [Convergent Intelligence66](https://savrn.com/models?publisher=reaperdoesntknow)
- [Yurun Yuan66](https://savrn.com/models?publisher=yurunyyr)
- [Google64](https://savrn.com/models?publisher=google)
- [Yurun Yuan62](https://savrn.com/models?publisher=yuruny)
- [Firza Hadzami61](https://savrn.com/models?publisher=firzahdzm)
- [Christopher Subia-Waud60](https://savrn.com/models?publisher=cwaud)
- [Yurun Yuan60](https://savrn.com/models?publisher=yyuan244)
- [Zeyuan Yang59](https://savrn.com/models?publisher=miiche)
- [Yanggangu57](https://savrn.com/models?publisher=yanggangu)
- [Hongao56](https://savrn.com/models?publisher=cisco1963)
- [Szekely53](https://savrn.com/models?publisher=attila115)
- [Francesca Padovani53](https://savrn.com/models?publisher=francesca9805)
- [Khazzz1c53](https://savrn.com/models?publisher=khazic)
- [Alfred Smith52](https://savrn.com/models?publisher=alfred8995)
- [NVIDIA50](https://savrn.com/models?publisher=nvidia)
- [Wang49](https://savrn.com/models?publisher=davidwdw)

[Most downloaded](https://savrn.com/models?sort=downloads)[Most liked](https://savrn.com/models?sort=likes)[Recently updated](https://savrn.com/models?sort=updated)[Name](https://savrn.com/models?sort=name)[Largest](https://savrn.com/models?sort=params)

12,870 models, sorted by most downloaded.

Model

### [Conformer-CTC](https://savrn.com/models/conformer-ctc)

[Yuxiang Mei](https://savrn.com/model-publishers/yuceong-may)

Open weights apache-2.0

[View model](https://savrn.com/models/conformer-ctc)

Model · Speech recognition

### [Confucius4-R2T2-CoreML-ANE](https://savrn.com/models/confucius4-r2t2-coreml-ane)

[Pedro Nascimento](https://savrn.com/model-publishers/lunks)

(a real-time speech-recognition fine-tune of Qwen3-ASR-1.7B, 30 languages) converted to Core ML programs that run on the Apple Neural Engine: the audio encoder in fp16, the Qwen3 decoder and the LM head palettised to 8 bits. 4.09 GB of bfloat16 becomes 2.8 GB on disk; while loaded, the Neural Engine holds the weights dequantised to fp16, about 4.5 GB, outside the process. Converted with the pipeline in the VoiceInk fork's tools/r2t2-coreml: the encoder through coremltools 9 with a fixed 800-frame window (the fused gelu replaced by a tanh formulation, whose constant absolute error otherwise swamps this encoder's small activations), the decoder through ANEMLL as two stateful chunks whose KV…

Open weights other coreml

[View model](https://savrn.com/models/confucius4-r2t2-coreml-ane)

Model · Speech recognition

### [Confucius4-R2T2-Q4_K_M-GGUF](https://savrn.com/models/confucius4-r2t2-q4-k-m-gguf)

[Dorian](https://savrn.com/model-publishers/nairod785)

Optimized Q4KM GGUF quantization of NetEase Youdao Confucius4-R2T2, a low-latency, append-only streaming ASR model (fine-tuned from Qwen3-ASR-1.7B with Longest Stable Prefix decoding), ready for native execution in transcribe.cpp and audio.cpp. Previous GGUF releases were constrained to Q80 or higher because uniform 4-bit and 5-bit quantizations either suffered from catastrophic empty-output cliffs or exhibited silent language drift (e.g. flipping to English when transcribing German or Russian). This release introduces an asymmetric per-tensor quantization recipe that breaks through that barrier: For the full ablation study, complete empirical test tables across 20+ quantization arms…

Open weights other transcribe.cpp

[View model](https://savrn.com/models/confucius4-r2t2-q4-k-m-gguf)

Model

### [ConnectIO-LSD](https://savrn.com/models/connectio-lsd)

[Fenghua](https://savrn.com/model-publishers/happyhua1)

One bundle per dataset or joint training collection, selected by the highest recorded iteration per required model stage. All files are inference-only exports from existing checkpoints; every tensor is exactly equal to its source. Selection does not establish the best validation score. The joint training collection contains E1Sp2D1SOG, E1Sp3D1, E1Sp5D3, E5Sp7D1, E8W1CB and E8W6SOG. It is one shared model, not six independently trained models. Spider baseline files were reconstructed from the highest-iteration original TensorFlow checkpoints. DigSpider is a separate fine-tuned pair; keep its LSD 20,000 context with ACRLSD 5,000. Install ConnectIO with its LSD dependencies. Use the…

Open weights pytorch

[View model](https://savrn.com/models/connectio-lsd)

Model

### [ConnectIO-Synful](https://savrn.com/models/connectio-synful)

[Fenghua](https://savrn.com/model-publishers/happyhua1)

e1sp5d3/paired600000.pt retains the trained indicator and partner-vector networks in one independent-single-task-pair checkpoint at recorded step 600,000. Both original encoders are preserved. E1Sp5D3 identifies the project's configured use dataset; it does not establish the original pretraining dataset or independent test performance. Two-step functional-test fine-tunes were excluded from this distribution. Install ConnectIO with synful-pytorch dependencies. Copy the model section from e1sp5d3/paired600000.config.json into your Synful run configuration; the generic example architecture may differ. Configure raw, coordinate geometry, ROI and a fresh output directory. Synful uses ZYX…

Open weights pytorch

[View model](https://savrn.com/models/connectio-synful)

Model · Robotics

### [ContentVault](https://savrn.com/models/contentvault)

[Lucky Robots](https://savrn.com/model-publishers/luckyrobots)

Content packs for Lucky Robots. Each pack contains a metadata.yaml, a thumbnail.png, and a.zip with the pack contents. All content packs are served globally via Cloudflare CDN: A Cloudflare Worker (worker/) listens for webhooks from HuggingFace. When a push is made to this repo, the Worker: 2. Streams each file directly to Cloudflare R2 (no buffering, handles large zip files) 4. R2 serves the files through Cloudflare's CDN with a 30-day cache at 300+ edge locations worldwide - Don't use raw git push for large files — use the CLI/API instead. They handle LFS/Xet automatically. - 50 GB max per file on HuggingFace. Split larger files before uploading.

Open weights mit

[View model](https://savrn.com/models/contentvault)

Model

### [CooWAIM](https://savrn.com/models/coowaim)

[COWARobot](https://savrn.com/model-publishers/cowarobot)

Open weights

[View model](https://savrn.com/models/coowaim)

Model

### [Cosmos3-Nano](https://savrn.com/models/cosmos3-nano)

[Ares Realm Studios](https://savrn.com/model-publishers/ares-realm-studios)

NVIDIA Cosmos™ is a world foundation model platform designed to accelerate the development of Physical AI by enabling machines to understand, simulate, and interact with the physical world across robotics, autonomous driving, and smart space environments, including industrial and factory-scale applications. Cosmos3 is a collection of Omnimodal world models capable of generating dynamic, high-quality video, image, audio, and action commands from combinations of text, image, video, and action trajectory inputs. It serves as a foundational building block for a broad range of Physical AI applications and research spanning world understanding, world generation, simulation, and embodied policy…

Open weights other 15.8B parameters 262,144 tokens cosmos

[View model](https://savrn.com/models/cosmos3-nano)

Model · Text to image

### [Cosmos3-Super-Text2Image](https://savrn.com/models/cosmos3-super-text2image)

[Ares Realm Studios](https://savrn.com/model-publishers/ares-realm-studios)

NVIDIA Cosmos™ is a world foundation model platform designed to accelerate the development of Physical AI by enabling machines to understand, simulate, and interact with the physical world across robotics, autonomous driving, and smart space environments, including industrial and factory-scale applications. Cosmos3 is a collection of Omnimodal world models capable of generating dynamic, high-quality video, image, audio, and action commands from combinations of text, image, video, and action trajectory inputs. It serves as a foundational building block for a broad range of Physical AI applications and research spanning world understanding, world generation, simulation, and embodied policy…

Open weights other 64.6B parameters 262,144 tokens cosmos

[View model](https://savrn.com/models/cosmos3-super-text2image)

Model · Text to speech

### [CosyVoice-300M](https://savrn.com/models/cosyvoice-300m)

[losCrossos](https://savrn.com/model-publishers/loscrossos)

Fun-CosyVoice 3.0 is an advanced text-to-speech (TTS) system based on large language models (LLM), surpassing its predecessor (CosyVoice 2.0) in content consistency, speaker similarity, and prosody naturalness. It is designed for zero-shot multilingual speech synthesis in the wild. - [x] release Fun-CosyVoice3-0.5B-2512 base model, rl model and its training/inference script - [x] release Fun-CosyVoice3-0.5B modelscope gradio space - [x] Thanks to the contribution from NVIDIA Yuekai Zhang, add triton trtllm runtime support and cosyvoice2 grpo training support - [x] release Fun-CosyVoice 3.0 eval set - [x] add CosyVoice2-0.5B vllm support - [x] 25hz CosyVoice2-0.5B released - [x] 25hz…

Open weights apache-2.0

[View model](https://savrn.com/models/cosyvoice-300m)

Model

### [CrowKrow](https://savrn.com/models/crowkrow)

[Mulemp](https://savrn.com/model-publishers/mulemp)

Access requested at publisher

[View model](https://savrn.com/models/crowkrow)

Model

### [Crown-Nikke-Eng-VA](https://savrn.com/models/crown-nikke-eng-va)

[Liberalio](https://savrn.com/model-publishers/liberalio-heretic)

Open weights

[View model](https://savrn.com/models/crown-nikke-eng-va)

Model · Image and text to text

### [Crystal-31B-RL](https://savrn.com/models/crystal-31b-rl)

[HiWaifu Research](https://savrn.com/model-publishers/hiwaifu-research)

Open weights apache-2.0 31.3B parameters transformers

[View model](https://savrn.com/models/crystal-31b-rl)

Model

### [CutIA-Qwen-4B-InstructInit-TF-EduHigh4Only](https://savrn.com/models/cutia-qwen-4b-instructinit-tf-eduhigh4only)

[brLLMmodels](https://savrn.com/model-publishers/g4me)

This model is a trained version of Qwen/Qwen3-4B-Instruct-2507. This is an experimental checkpoint.

Open weights 4.4B parameters 40,960 tokens

[View model](https://savrn.com/models/cutia-qwen-4b-instructinit-tf-eduhigh4only)

Model

### [CuttyMOA-1.3-GGUF](https://savrn.com/models/cuttymoa-1-3-gguf)

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

static quants of https://huggingface.co/sayeed105236/CuttyMOA-1.3

Open weights

[View model](https://savrn.com/models/cuttymoa-1-3-gguf)

Model

### [Cyber-F1-AWQ-smoke-prod](https://savrn.com/models/cyber-f1-awq-smoke-prod)

[Autumn](https://savrn.com/model-publishers/autumn10)

Open weights 35.1B parameters 262,144 tokens

[View model](https://savrn.com/models/cyber-f1-awq-smoke-prod)

Model · Text generation

### [CyberStag-Security-26B-A4B-V1-Uncensored-Heretic-i1-GGUF](https://savrn.com/models/cyberstag-security-26b-a4b-v1-uncensored-heretic-i1-gguf)

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

weighted/imatrix quants of https://huggingface.co/OS-Software/CyberStag-Security-26B-A4B-V1-Uncensored-Heretic For a convenient overview and download list, visit our model page for this model. static quants are available at https://huggingface.co/mradermacher/CyberStag-Security-26B-A4B-V1-Uncensored-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/cyberstag-security-26b-a4b-v1-uncensored-heretic-i1-gguf)

Model · Text generation

### [Cyberdonia-24B-v8](https://savrn.com/models/cyberdonia-24b-v8)

[Naphula](https://savrn.com/model-publishers/naphula)

/ Cockpit & Void Palette / / Hyperspace & Instrument Lights / / Low-framerate flicker keyframes (stepped timing) / / Deep radial hyperspace tunnel backdrop through cockpit window glass / radial-gradient(circle at 50% 45%, rgba(255, 230, 150, 0.25) 0%, rgba(255, 42, 75, 0.25) 18%, rgba(189, 0, 255, 0.2) 36%, rgba(0, 229, 255, 0.15) 54%, transparent 75%), repeating-conic-gradient(from 0deg at 50% 45%, #05070a 0deg 10deg, #0e131d 15deg, #05070a 20deg), radial-gradient(ellipse at center, transparent 30%, #000000 95%); / Low-framerate scanline overlay / / Heavy Flight Deck Chassis Container / 0 0 50px rgba(0, 0, 0, 0.9), inset 0 0 35px rgba(0, 0, 0, 0.8), inset 0 1px 0 rgba(255, 255, 255, 0.1)…

Open weights apache-2.0 23.6B parameters 131,072 tokens transformers

[View model](https://savrn.com/models/cyberdonia-24b-v8)

Model

### [Cybersecurity-LLM-Qwen3-32B-GGUF](https://savrn.com/models/cybersecurity-llm-qwen3-32b-gguf)

[I PUTU RIYAN SAPUTRA](https://savrn.com/model-publishers/riyan200324200324)

weighted/imatrix quants of https://huggingface.co/Trendyol/Trendyol-Cybersecurity-LLM-Qwen3-32B-Q80-GGUF static quants are available at https://huggingface.co/mradermacher/Trendyol-Cybersecurity-LLM-Qwen3-32B-Q80-GGUF-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/cybersecurity-llm-qwen3-32b-gguf)

Model · Object detection

### [CytoSPM](https://savrn.com/models/cytospm)

[Smitih](https://savrn.com/model-publishers/doilion111)

Model weights of CytoSPM: Open-Vocabulary Cytopathology Detection with Structured Prompt Bank (BIBM 2026). This is the model reported in the paper (Table III). The numbers above were measured with the released code on an RTX 3090; the paper values (33.55 / 52.20 / 38.17 and 15.00 / 21.00 / 17.20) were measured on an RTX 4090. Base AP is the COCO AP over the 24 base categories of PentaCyto; novel AP is the zero-shot COCO AP over the 9 held-out categories. The file contains model weights only (statedict) and loads with torch.load(..., weightsonly=True). See the code repository for installation, data preparation and training. The PentaCyto images and annotations are not included.

Open weights gpl-3.0

[View model](https://savrn.com/models/cytospm)

Model · Audio to audio

### [DAC-16kHz-LiteRT](https://savrn.com/models/dac-16khz-litert)

[LiteRT Community (FKA TFLite)](https://savrn.com/model-publishers/litert-community)

Descript Audio Codec running on-device on the LiteRT CompiledModel GPU (ML Drift). The convolutional encoder/decoder run on the GPU; the RVQ runs on CPU. 43:1 compression (1 s → 12×50 codes), RTF ≈ 0.82 (faster than real-time) on Pixel 8a. - dac16khzencoderfp16.tflite (43 MB) — audio[1,1,16000] → latent[1,1024,50], GPU. - dac16khzdeconlyzsfp16.tflite (105 MB) — latent[1,1024,50] → audio, GPU. - dacrvq.bin (1.2 MB) — RVQ weights (12 codebooks) for the CPU quantizer (float32 LE). encoder 367/367 + decoder 398/398 nodes on the LiteRT GPU delegate (LITERTCL, 1 partition, no CPU fallback); warm RTF ~0.82; reconstruction corr 1.0 vs PyTorch DAC. The decoder's ConvTranspose1d are rewritten to a…

Open weights mit litert

[View model](https://savrn.com/models/dac-16khz-litert)

Model · Text to speech

### [DACFlow-EN-10k](https://savrn.com/models/dacflow-en-10k)

[VoiceHub](https://savrn.com/model-publishers/voicehub)

DACFlow-EN-10k reads English text aloud in a voice you choose. Give it a short recording of a voice (3-10 seconds, with the exact words spoken in it) and any English text, and it speaks that text in that voice. This is zero-shot voice cloning: the voice does not have to be in the training data. The output is 48 kHz audio. The model has 206 M parameters and is trained from scratch only on the provided data: 9,543 hours of synthetic English speech (3,400,911 clips, 3,587 voices) from SynDataLab-EN/echo-clones-4m-en (the curated part of its ~11,150 hours), nothing else. A hobby project; the weights are apache-2.0. The name: DAC for the Semantic-DACVAE audio codec whose latents it generates…

Open weights apache-2.0 audioseal

[View model](https://savrn.com/models/dacflow-en-10k)

Model · Text generation

### [DC-Jev-RL](https://savrn.com/models/dc-jev-rl)

[Zhang Ziyang](https://savrn.com/model-publishers/huanguang)

Open weights apache-2.0 peft

[View model](https://savrn.com/models/dc-jev-rl)

Model · Text generation

### [DCore-DFlare-Qwen3-4B-Budget16](https://savrn.com/models/dcore-dflare-qwen3-4b-budget16)

[Wingchiuloong](https://savrn.com/model-publishers/wingchiuloong)

Open weights 531M parameters transformers

[View model](https://savrn.com/models/dcore-dflare-qwen3-4b-budget16)

## Model Collections

Hand-picked starting points, each with the reason it exists.

Collection · 4 entries

### [Embedding models for retrieval](https://savrn.com/collections/embedding-models-for-retrieval)

Sentence and document embedding models used to build retrieval systems. Dimension and sequence length matter more than size here, and both come from the publisher.

[View collection](https://savrn.com/collections/embedding-models-for-retrieval)

Collection · 4 entries

### [Models that fit on one accelerator](https://savrn.com/collections/models-that-run-on-one-accelerator)

Models whose publisher-reported parameter count puts them within reach of a single accelerator at common precisions. Memory needed depends on precision and serving configuration, so treat the parameter count as the starting point, not the answer.

[View collection](https://savrn.com/collections/models-that-run-on-one-accelerator)

Collection · 6 entries

### [Open-weight text models worth knowing](https://savrn.com/collections/open-weight-text-models-worth-knowing)

Widely used open-weight language models, chosen because each one is a distinct family rather than a variant of the one above it. Selection, not a ranking.

[View collection](https://savrn.com/collections/open-weight-text-models-worth-knowing)

Collection · 3 entries

### [Speech and audio models](https://savrn.com/collections/speech-and-audio)

Recognition and synthesis models, grouped so the two directions are easy to compare.

[View collection](https://savrn.com/collections/speech-and-audio)

## Open-Weight Models Explained

### What is an open-weight model?

An AI model whose trained weights are published for anyone to download, so it can be run, tested and fine-tuned on hardware the user controls.

### Is an open-weight model the same as open source?

Not always. Open weights means the trained model can be downloaded. Open source usually also means the training code and data are available and the license allows broad reuse. Many open-weight models release the weights only.

### Can I use an open-weight model commercially?

It depends on the license. Apache 2.0 and MIT allow commercial use. Other licenses limit it, for example to non-commercial use or below a set number of users. Every model page here shows its license.

### How much memory does an open-weight model need?

About two bytes per parameter at 16-bit precision, so a 7-billion-parameter model needs roughly 14 GB for its weights, plus memory for the context it processes. Each model page lists its parameter count and the size of its files.

## Related SAVRN Research

The hub sits beside SAVRN's market data and infrastructure research: what models cost to run, and what it takes to run them.

SAVRN Index

### [What open models cost to run](https://savrn.com/ai-index/pricing/open-models)

The same open-weight model priced by every host that serves it, per million tokens.

Research Hub

### [Data center trackers and maps](https://savrn.com/data-center-research)

Moratoriums, permits, power, water and capital behind the facilities that run these models.

Method

### [How the Model Hub is built](https://savrn.com/model-hub/methodology)

Sources, evidence labels, refresh behaviour, and the limits of every comparison here.