# Models, Page 240 of 512
Source: https://savrn.com/models/page/240
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.

12,283Models

3,510Datasets

290Papers

7,436Publishers

12,632Sourced relationships

Updated 2026-10-22 · [How the library is built](https://savrn.com/model-hub/methodology)

## Filter Models

Task

- [Text generation1,506](https://savrn.com/models?task=Text+generation)
- [Image and text to text560](https://savrn.com/models?task=Image+and+text+to+text)
- [Feature extraction396](https://savrn.com/models?task=Feature+extraction)
- [Robotics379](https://savrn.com/models?task=Robotics)
- [Text classification328](https://savrn.com/models?task=Text+classification)
- [Text to image228](https://savrn.com/models?task=Text+to+image)
- [Speech recognition185](https://savrn.com/models?task=Speech+recognition)
- [Text to speech143](https://savrn.com/models?task=Text+to+speech)
- [Image classification139](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)
- [Token classification99](https://savrn.com/models?task=Token+classification)
- [Reinforcement learning97](https://savrn.com/models?task=Reinforcement+learning)
- [Zero-shot classification93](https://savrn.com/models?task=Zero-shot+classification)
- [Image segmentation90](https://savrn.com/models?task=Image+segmentation)
- [Object detection86](https://savrn.com/models?task=Object+detection)
- [Any to any79](https://savrn.com/models?task=Any+to+any)
- [Translation79](https://savrn.com/models?task=Translation)
- [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 classification60](https://savrn.com/models?task=Video+classification)
- [Image to text59](https://savrn.com/models?task=Image+to+text)
- [Text to video55](https://savrn.com/models?task=Text+to+video)

Library

- [transformers2,947](https://savrn.com/models?library=transformers)
- [peft361](https://savrn.com/models?library=peft)
- [diffusers202](https://savrn.com/models?library=diffusers)
- [pytorch194](https://savrn.com/models?library=pytorch)
- [gguf181](https://savrn.com/models?library=gguf)
- [mlx157](https://savrn.com/models?library=mlx)
- [lerobot150](https://savrn.com/models?library=lerobot)
- [sentence-transformers139](https://savrn.com/models?library=sentence-transformers)
- [timm49](https://savrn.com/models?library=timm)
- [llama.cpp45](https://savrn.com/models?library=llama.cpp)
- [transformers.js45](https://savrn.com/models?library=transformers.js)
- [flaxspeaker44](https://savrn.com/models?library=flaxspeaker)
- [onnx40](https://savrn.com/models?library=onnx)
- [vllm40](https://savrn.com/models?library=vllm)
- [openpi35](https://savrn.com/models?library=openpi)
- [diffusion-single-file29](https://savrn.com/models?library=diffusion-single-file)
- [minimax-h327](https://savrn.com/models?library=minimax-h3)
- [ultralytics24](https://savrn.com/models?library=ultralytics)
- [PaddleOCR22](https://savrn.com/models?library=PaddleOCR)
- [exllamav320](https://savrn.com/models?library=exllamav3)
- [openvino20](https://savrn.com/models?library=openvino)
- [coreml18](https://savrn.com/models?library=coreml)
- [litert17](https://savrn.com/models?library=litert)
- [keras15](https://savrn.com/models?library=keras)

Modality

- [Other7,017](https://savrn.com/models?modality=Other)
- [Text2,788](https://savrn.com/models?modality=Text)
- [Image and text619](https://savrn.com/models?modality=Image+and+text)
- [Image593](https://savrn.com/models?modality=Image)
- [Audio476](https://savrn.com/models?modality=Audio)
- [Control476](https://savrn.com/models?modality=Control)
- [Video115](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-2.03,285](https://savrn.com/models?license=apache-2.0)
- [mit1,305](https://savrn.com/models?license=mit)
- [other759](https://savrn.com/models?license=other)
- [cc-by-nc-4.0209](https://savrn.com/models?license=cc-by-nc-4.0)
- [cc-by-4.0164](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-4.052](https://savrn.com/models?license=cc-by-nc-sa-4.0)
- [llama3.240](https://savrn.com/models?license=llama3.2)
- [agpl-3.032](https://savrn.com/models?license=agpl-3.0)
- [unknown32](https://savrn.com/models?license=unknown)
- [llama3.128](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++17](https://savrn.com/models?license=openrail%2B%2B)
- [openmdw-1.115](https://savrn.com/models?license=openmdw-1.1)
- [llama314](https://savrn.com/models?license=llama3)
- [openrail14](https://savrn.com/models?license=openrail)
- [cc-by-nc-nd-4.013](https://savrn.com/models?license=cc-by-nc-nd-4.0)
- [creativeml-openrail-m13](https://savrn.com/models?license=creativeml-openrail-m)
- [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 weights11,872](https://savrn.com/models?access=open_access)
- [Access requested at publisher411](https://savrn.com/models?access=gated)

Publisher

- [Team Mradermacher324](https://savrn.com/models?publisher=mradermacher)
- [Yurun Yuan110](https://savrn.com/models?publisher=ryanyr)
- [RunningHub.ai102](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)
- [Google64](https://savrn.com/models?publisher=google)
- [Yurun Yuan64](https://savrn.com/models?publisher=yurunyyr)
- [Firza Hadzami61](https://savrn.com/models?publisher=firzahdzm)
- [Yurun Yuan61](https://savrn.com/models?publisher=yuruny)
- [Zeyuan Yang59](https://savrn.com/models?publisher=miiche)
- [Yanggangu57](https://savrn.com/models?publisher=yanggangu)
- [Yurun Yuan57](https://savrn.com/models?publisher=yyuan244)
- [Hongao56](https://savrn.com/models?publisher=cisco1963)
- [Francesca Padovani53](https://savrn.com/models?publisher=francesca9805)
- [Alfred Smith52](https://savrn.com/models?publisher=alfred8995)
- [Szekely52](https://savrn.com/models?publisher=attila115)
- [Khazzz1c52](https://savrn.com/models?publisher=khazic)
- [Christopher Subia-Waud50](https://savrn.com/models?publisher=cwaud)
- [Wang49](https://savrn.com/models?publisher=davidwdw)
- [NVIDIA49](https://savrn.com/models?publisher=nvidia)

[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)

12,283 models, sorted by most downloaded.

Model · Image and text to text

### [ViSkill-Sokoban](https://savrn.com/models/viskill-sokoban)

[Hongxing Li](https://savrn.com/model-publishers/hongxingli)

This repository contains ViSkill-Sokoban and its visual skill library, introduced in ViSkill: Reinforcing VLM Agents with Evolving Visual-Native Skills. ViSkill-Sokoban is a visual agent model for Sokoban, built upon Qwen2.5-VL-3B-Instruct. It represents successful interactions as reusable visual skill cards. Geometry-aware retrieval guides the agent, while PPO with skill-guided rewards and online skill distillation jointly improve the policy and skill library. Model files are stored at the repository root, with the accompanying visual skill library in skilllibrary/. For the full ViSkill agent pipeline, including skill retrieval and environment interaction, please refer to our code…

Open weights 4.1B parameters 128,000 tokens transformers

[View model](https://savrn.com/models/viskill-sokoban)

Model

### [ViVeAI](https://savrn.com/models/viveai)

[Nguyen](https://savrn.com/model-publishers/ntthuybentre-debug)

Open weights

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

Model · Speech recognition

### [VibeVoice-ASR-AWQ-W4A16-ASYM-DFlash2](https://savrn.com/models/vibevoice-asr-awq-w4a16-asym-dflash2)

[Nikita Davidchuk](https://savrn.com/model-publishers/ar4ikov)

VibeVoice-ASR (7B), AWQ W4A16 (asymmetric, groups of 128), with its DFlash 2 drafter bundled in drafter/: one download, and vibevoice.c decodes with speculative decoding -- the drafter proposes 8 tokens in one pass, the model checks them in one pass and keeps the ones it agrees with. the model's own decode step, so the transcript is byte-for-byte the one without the drafter. (With a drafter vibevoice.c attends with flashinfer, which checks rows together; the transcript is then --attn flashinfer's.) Needs vibevoice.c with DFlash 2 support: branch dflash2 (PR #48), in the next release. A model directory's drafter/ is used without asking: vibevoice.c b72be15 (branch dflash2), RTX 3090, greedy…

Open weights mit 8.3B parameters vibevoice.c

[View model](https://savrn.com/models/vibevoice-asr-awq-w4a16-asym-dflash2)

Model · Speech recognition

### [VibeVoice-ASR-DFlash2](https://savrn.com/models/vibevoice-asr-dflash2)

[Nikita Davidchuk](https://savrn.com/model-publishers/ar4ikov)

VibeVoice-ASR (7B), the original BF16 weights as Microsoft published them, with its DFlash 2 drafter bundled in drafter/: one download, and vibevoice.c decodes with speculative decoding -- the drafter proposes 8 tokens in one pass, the model checks them in one pass and keeps the ones it agrees with. the model's own decode step, so the transcript is byte-for-byte the one without the drafter. (With a drafter vibevoice.c attends with flashinfer, which checks rows together; the transcript is then --attn flashinfer's.) Needs vibevoice.c with DFlash 2 support: branch dflash2 (PR #48), in the next release. A model directory's drafter/ is used without asking: vibevoice.c runs BF16 weights as dense…

Open weights mit 8.7B parameters vibevoice.c

[View model](https://savrn.com/models/vibevoice-asr-dflash2)

Model · Speech recognition

### [VibeVoice-ASR-DFlash2-Drafter](https://savrn.com/models/vibevoice-asr-dflash2-drafter)

[Nikita Davidchuk](https://savrn.com/model-publishers/ar4ikov)

A DFlash 2 block drafter for VibeVoice-ASR (7B) (Ar4ikov/VibeVoice-ASR-AWQ-W4A16-ASYM), for speculative decoding in vibevoice.c. It proposes 8 tokens in one pass; vibevoice.c checks them in one pass of the model and keeps the ones the model agrees with, plus one of its own. the model's own one-token decode step, so the transcript with this drafter is byte-for-byte the transcript without it — words, timestamps, speakers. The drafter only changes how many passes it takes. One thing changes with --draft: vibevoice.c then attends with flashinfer (--attn auto picks it), because flashinfer checks several rows in one pass over the cache where the default fa2 walks it once per row. The transcript…

Open weights mit 831M parameters 131,072 tokens vibevoice.c

[View model](https://savrn.com/models/vibevoice-asr-dflash2-drafter)

Model · Speech recognition

### [VibeVoice-ASR-DFlash2-Drafter-AWQ-W4A16-ASYM](https://savrn.com/models/vibevoice-asr-dflash2-drafter-awq-w4a16-asym)

[Nikita Davidchuk](https://savrn.com/model-publishers/ar4ikov)

A DFlash 2 block drafter for VibeVoice-ASR (7B) (Ar4ikov/VibeVoice-ASR-AWQ-W4A16-ASYM), for speculative decoding in vibevoice.c. It proposes 8 tokens in one pass; vibevoice.c checks them in one pass of the model and keeps the ones the model agrees with, plus one of its own. the model's own one-token decode step, so the transcript with this drafter is byte-for-byte the transcript without it — words, timestamps, speakers. The drafter only changes how many passes it takes. One thing changes with --draft: vibevoice.c then attends with flashinfer (--attn auto picks it), because flashinfer checks several rows in one pass over the cache where the default fa2 walks it once per row. The transcript…

Open weights mit 832M parameters 131,072 tokens vibevoice.c

[View model](https://savrn.com/models/vibevoice-asr-dflash2-drafter-awq-w4a16-asym)

Model

### [Victoria-canada-r5](https://savrn.com/models/victoria-canada-r5)

[Ryan Monsurate](https://savrn.com/model-publishers/rmonsurate)

Working checkpoints from a Canadian fine-tune of Victoria; not a release.

Open weights

[View model](https://savrn.com/models/victoria-canada-r5)

Model

### [VideoNature](https://savrn.com/models/videonature)

[Sjk](https://savrn.com/model-publishers/jmpplbp)

Runtime assets use neutral filenames. This is an application package; underlying components retain their original licenses and authorship.

Open weights

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

Model

### [Video_1](https://savrn.com/models/video-1)

[Marvelic](https://savrn.com/model-publishers/topgunm)

Open weights

[View model](https://savrn.com/models/video-1)

Model

### [VieNeu-TTS-v3-Nano-CoreML](https://savrn.com/models/vieneu-tts-v3-nano-coreml)

[Buu DVH](https://savrn.com/model-publishers/raikiri1498)

Open weights apache-2.0

[View model](https://savrn.com/models/vieneu-tts-v3-nano-coreml)

Model · Text generation

### [Vigyan-2B-STEM-Instruct-v1](https://savrn.com/models/vigyan-2b-stem-instruct-v1)

[Shreyansh singh](https://savrn.com/model-publishers/shreyansh12183)

Developed by Vigyan AI in Varanasi, Uttar Pradesh, India. Vigyan-2B-STEM-Instruct-v1 is India's sovereign edge Small Language Model (SLM) engineered specifically for low-latency, edge-deployable STEM reasoning. At ~2.4 billion parameters, it delivers: 1. Ultra-Low VRAM Footprint: Requires only ~1.8 GB VRAM in 4-bit NF4 precision, making it deployable on consumer laptops, edge gateways, Raspberry Pi 5, and mobile devices. 2. Sub-Second Token Generation: Yields 45–60 tokens/second on a single GPU, enabling real-time interactive STEM tutoring and on-device circuit debugging. 3. Structured Tool Calling: Trained to invoke deterministic Python execution blocks ( ) for exact arithmetic…

Open weights cc-by-nc-4.0

[View model](https://savrn.com/models/vigyan-2b-stem-instruct-v1)

Model · Text generation

### [Vigyan-7B-STEM-DPO-v1](https://savrn.com/models/vigyan-7b-stem-dpo-v1)

[Shreyansh singh](https://savrn.com/model-publishers/shreyansh12183)

Developed by Vigyan AI in Varanasi, Uttar Pradesh, India. Vigyan-7B-STEM-DPO-v1 is a specialized 7-billion parameter language model trained on deep engineering and physical sciences. Unlike general-purpose foundation models that guess mathematical calculations through token auto-regression, Vigyan-7B is aligned using Direct Preference Optimization (DPO) to: 1. Eliminate Arithmetic Drift: Active negative preference margins suppress probabilistic token guessing for quantitative operations. 2. Enforce Physical Conservation Laws: Enforces physical invariant guardrails (e.g., $|\Gamma| \le 1.0$, $\eta{\text{Carnot}} 0$, $v{\text{orbit}} > 0$). 3. Structured Tool Invocations: Trained to emit…

Open weights cc-by-nc-4.0

[View model](https://savrn.com/models/vigyan-7b-stem-dpo-v1)

Model

### [Vigyan-Pro-Studio](https://savrn.com/models/vigyan-pro-studio)

[Shreyansh singh](https://savrn.com/model-publishers/shreyansh12183)

Vigyan Pro is a private, 100% offline AI and interactive 3D science studio built at ExperimentLab.in for engineers, students, and researchers. - 3D Models & Design (/cad3d): Inspect interactive 3D gears, molecules, and structures directly inside your conversation. - Math & Graphs (/plot, /mathvisual, /derive): Plot functions, visualize 3D surfaces, and solve equations step-by-step. - Physics & Circuits (/simulate, /circuit, /semiconductor): Run live motion, orbital, and electronic circuit simulations at 60 FPS. - Science & Biology (/biology, /material, /medical): Explore 3D DNA double helices, crystal lattices, and clinical biomarker panels. - Smart GPU + CPU Hybrid Engine: Automatically…

Open weights other

[View model](https://savrn.com/models/vigyan-pro-studio)

Model

### [Viko-Light-1](https://savrn.com/models/viko-light-1)

[Eliasar jaco Moncada Gómez](https://savrn.com/model-publishers/eliasar112)

Open weights

[View model](https://savrn.com/models/viko-light-1)

Model

### [Vinci-Cyber-30B-1.0-GGUF](https://savrn.com/models/vinci-cyber-30b-1-0-gguf)

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

static quants of https://huggingface.co/simpledirect/Vinci-Cyber-30B-1.0 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/vinci-cyber-30b-1-0-gguf)

Model

### [Vinci-MLE-8B-1.0-i1-GGUF](https://savrn.com/models/vinci-mle-8b-1-0-i1-gguf)

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

weighted/imatrix quants of https://huggingface.co/simpledirect/Vinci-MLE-8B-1.0 For a convenient overview and download list, visit our model page for this model. static quants are available at https://huggingface.co/mradermacher/Vinci-MLE-8B-1.0-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/vinci-mle-8b-1-0-i1-gguf)

Model

### [Virtues-1](https://savrn.com/models/virtues-1)

[Zeto AI](https://savrn.com/model-publishers/zetoai)

Open weights apache-2.0

[View model](https://savrn.com/models/virtues-1)

Model · Text generation

### [Viu-1.5B-MoE](https://savrn.com/models/viu-1-5b-moe)

[Vipin Kumar](https://savrn.com/model-publishers/viuai)

Viu-1.5B-MoE is a sovereign Indian Large Language Model featuring a 48-Layer Ultra-Deep Frontier Mixture of Experts (MoE) architecture designed for deep hierarchical reasoning, Indic multilingual fluency (Hindi, Hinglish, English), and high-speed on-device inference. 1. 48-Layer Ultra-Deep Reasoning: Deep hierarchical abstraction across 4 cognitive tiers (12 layers each: Token Mechanics $\rightarrow$ Multilingual Alignment $\rightarrow$ Domain Knowledge $\rightarrow$ Deep Deductive Logic). 2. Compressed Sparse Attention 2 (CSA2): DeepSeek-V4.1 style low-rank KV compression saving 80% KV-cache memory for long-context inference on consumer GPUs. 3. Manifold-Constrained Hyper-Connections…

Open weights apache-2.0

[View model](https://savrn.com/models/viu-1-5b-moe)

Model · Text generation

### [ViuMini-MoE-242M](https://savrn.com/models/viumini-moe-242m)

[Vipin Kumar](https://savrn.com/model-publishers/viuai)

Viu-1.5B-MoE is a sovereign Indian Large Language Model featuring a 48-Layer Ultra-Deep Frontier Mixture of Experts (MoE) architecture designed for deep hierarchical reasoning, Indic multilingual fluency (Hindi, Hinglish, English), and high-speed on-device inference. 1. 48-Layer Ultra-Deep Reasoning: Deep hierarchical abstraction across 4 cognitive tiers (12 layers each: Token Mechanics $\rightarrow$ Multilingual Alignment $\rightarrow$ Domain Knowledge $\rightarrow$ Deep Deductive Logic). 2. Compressed Sparse Attention 2 (CSA2): DeepSeek-V4.1 style low-rank KV compression saving 80% KV-cache memory for long-context inference on consumer GPUs. 3. Manifold-Constrained Hyper-Connections…

Open weights apache-2.0

[View model](https://savrn.com/models/viumini-moe-242m)

Model

### [Vivy-R-SWE-Code-3B-GGUF](https://savrn.com/models/vivy-r-swe-code-3b-gguf)

[Nguyễn Văn Vĩ](https://savrn.com/model-publishers/vinguyen0891)

Open weights apache-2.0

[View model](https://savrn.com/models/vivy-r-swe-code-3b-gguf)

Model

### [Vivy-R-Science-Bio-3B-GGUF](https://savrn.com/models/vivy-r-science-bio-3b-gguf)

[Nguyễn Văn Vĩ](https://savrn.com/model-publishers/vinguyen0891)

Open weights apache-2.0

[View model](https://savrn.com/models/vivy-r-science-bio-3b-gguf)

Model

### [VocalCoreTry3](https://savrn.com/models/vocalcoretry3)

[Mistyeyed](https://savrn.com/model-publishers/user-misty-mist)

Open weights cc-by-nc-4.0

[View model](https://savrn.com/models/vocalcoretry3)

Model

### [VoiceConversionWebUI](https://savrn.com/models/voiceconversionwebui)

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

Open weights mit

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

Model

### [VoiceTut-TTS-GGUF](https://savrn.com/models/voicetut-tts-gguf)

[Mohammed Aly](https://savrn.com/model-publishers/mohammedaly22)

Open weights

[View model](https://savrn.com/models/voicetut-tts-gguf)

## 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.