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.
Updated 2026-10-22 · How the library is built
12,283 models, sorted by most downloaded.
Ternary (1.58-bit) language model in GGUF Q20 format for llama.cpp - Demo repo — examples for serving, benchmarking, and integrating Bonsai - Discord — community support and updates Each weight takes a value from {-1, 0, +1}, with one shared FP16 scale per group of 128 weights: Q20 encodes each weight as a 2-bit code q in {0, 1, 2, 3}, dequantized via w = (q - 1) scale. One 128-element block is 34 bytes (2 bytes FP16 scale + 32 bytes of packed 2-bit codes) for an effective 2.125 bits/weight. The fourth code point (q = 3, reconstructing to +2 scale) is reserved for future extensions; for ternary weights it is unused. Evaluated with EvalScope v1.4.2 + vLLM 0.15.1 on NVIDIA H100 under…
static quants of https://huggingface.co/migtissera/Tess-3-Mixtral-8x22B For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants are available at https://huggingface.co/mradermacher/Tess-3-Mixtral-8x22B-i1-GGUF If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9…
45M CNN. Phases: SFT -> SF Distill -> On-Policy -> Endgame Self-Play.
This is an ONNX version of UX4567/Text-Summarizer-t5-small. It was automatically converted and uploaded using this Hugging Face Space. See the pipeline documentation for summarization: https://huggingface.co/docs/transformers.js/api/pipelines#modulepipelines.SummarizationPipeline This model is a fine-tuned version of T5 designed for abstractive text summarization. It condenses long articles, documents, or paragraphs into short, accurate, and context-aware summaries. You can load and test the model using the Hugging Face transformers pipeline or direct model classes: from transformers import pipeline summarizer = pipeline("text-generation", model="UX4567/Text-Summarizer-t5-small") text = """…
Security-domain specialized experimental preview. Headline. Security-domain specialized experimental preview. No statistically clear difference from the stock Qwen3-Embedding-8B baseline under the preregistered held-out evaluation. On general retrieval: no catastrophic regression under the preregistered 10% threshold; significant FiQA degradation was observed. Thaki-SecEmbed-8B is a LoRA specialization of Qwen/Qwen3-Embedding-8B. It retrieves ATT&CK technique documentation for security-analyst queries. Queries can be questions, claims, keywords, evidence requests, analyst searches, or TTP hypotheses, in English or Korean. - ATT&CK technique retrieval. Given a query, rank ATT&CK technique…
SmolVLA is a compact, efficient vision-language-action model that achieves competitive performance at reduced computational costs and can be deployed on consumer-grade hardware. This policy has been trained and pushed to the Hub using LeRobot. See the full documentation at LeRobot Docs. For a complete walkthrough, see the training guide. Below is the short version on how to train and run inference/eval: Writes checkpoints to outputs/train/ /checkpoints/. Prefix the dataset repo with eval\ and supply --policy.path pointing to a local or hub checkpoint.
ThinCtx by thinletter. ThinCtx-Qwen3.5-0.8B is the ThinCtx conversion of Qwen3.5-0.8B that keeps the GPU memory for the context small: it grows 20 to 30 times more slowly than the base model's cache (0.43 GB instead of 6.0 GB at half a million tokens). The part of the context kept on the GPU is small and grows slowly with the length of the conversation or document; the full context is kept in ordinary system memory. ThinCtx trades some speed for this (see Speed below). Chat and tool calling use the Qwen3.5 chat template. Runtime required. ThinCtx models run on the thinctx runtime (pip install thinctx, below). The runtime is what keeps the context memory small; other inference libraries do…
static quants of https://huggingface.co/thinletter/ThinCtx-Qwen3.5-4B For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants are available at https://huggingface.co/mradermacher/ThinCtx-Qwen3.5-4B-i1-GGUF If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 See…
weighted/imatrix quants of https://huggingface.co/thinletter/ThinCtx-Qwen3.5-4B For a convenient overview and download list, visit our model page for this model. static quants are available at https://huggingface.co/mradermacher/ThinCtx-Qwen3.5-4B-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…
Qwen3.5-2B that thinks less and answers better. ThinkLess-2B uses 57–82% fewer reasoning tokens than the base model on math and science benchmarks while being more accurate on GSM8K, MATH-500 and GPQA-Diamond, with almost no answers cut off mid-thought. Served with vLLM and its built-in MTP speculative decoding, a typical request finishes 3.4× faster than the base model. It was post-trained in two stages: SFT on the model's own shortest correct solutions (self-distillation, with a same-family 9B teacher filling in the hardest problems), then a short GRPO run with an accuracy-and-length reward. All accuracies are at Qwen's recommended 81,920-token thinking budget; see Evaluation. Mean…
FP8 version of ThinkLess-2B: 8-bit floating-point weights and activations, 2.5 GB (bf16: 4.3 GB), with near-identical accuracy. Made with llm-compressor (FP8DYNAMIC: per-channel FP8 weights, dynamic per-token FP8 activations, no calibration data). The output head, vision tower and MTP heads stay in 16-bit. The differences are within the 95% confidence intervals, and answers stay just as short (cut-offs ≤ 1%). FP8 compute needs a GPU with FP8 support (NVIDIA Hopper or Ada, e.g. H100, L4, RTX 40-series); vLLM loads the compressed-tensors format directly. Use Qwen3.5's thinking-mode sampling (temperature 1.0, top-p 0.95, top-k 20, presence penalty 1.5). A 4-bit AWQ version of ThinkLess-2B was…
Model Collections
Hand-picked starting points, each with the reason it exists.
Collection · 4 entries
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.
Collection · 4 entries
Models that fit 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.
Collection · 6 entries
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.
Collection · 3 entries
Speech and audio models
Recognition and synthesis models, grouped so the two directions are easy to compare.
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
The same open-weight model priced by every host that serves it, per million tokens.
Research Hub
Data center trackers and maps
Moratoriums, permits, power, water and capital behind the facilities that run these models.
Method
How the Model Hub is built
Sources, evidence labels, refresh behaviour, and the limits of every comparison here.