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 2026-10-24 · How the library is built
12,870 models, sorted by most downloaded.
These are vision-language-action (VLA) models fine-tuned on BimanualYAM manipulation tasks for the RoboColosseum benchmark. Each VLA is fine-tuned from its public base checkpoint with its repo-default recipe: default LRs and frozen parts, with the LR scaled linearly with the effective batch size, for 5 epochs. Each folder holds the final-epoch inference weights plus the small config files needed to load the model. Each / /README.md gives the recipe, the files, and how to load the model. Training logs are in the W&B project shaileshxml-nus/RoboColosseum.
static quants of https://huggingface.co/KelvinAxhcar/BitCache-Qwen2.5-0.5B-Instruct
It takes words and makes pictures Download them in the Files & versions tab.
It takes words and makes pictures Download them in the Files & versions tab.
laptop / single GPU · Vision-capable Bonsai 2 27B — PrismML's ternary compression of Qwen3.8-27B — with the refusal circuitry surgically removed at the weight level while capability, vision, reasoning modes (off/low/xhigh), tool use, and multi-turn coherence are preserved. Full 27B-class hybrid Attention + SSM (GatedDeltaNet) architecture in a 5.9 GB 1bit GGUF. Proprietary weight-level abliteration by the dealignai research team. Byte-identical to the base ternary quant everywhere except a small set of tensors that carry the refusal circuit. Drop-in replacement for the ternary base at inference — same tokenizer, same chat template, same reasoning modes, same vision projector interface.…
laptop / single GPU · Vision-capable Bonsai 2 27B — PrismML's ternary compression of Qwen3.8-27B — with the refusal circuitry surgically removed at the weight level while capability, vision, reasoning modes (off/low/xhigh), tool use, and multi-turn coherence are preserved. Full 27B-class hybrid Attention + SSM (GatedDeltaNet) architecture in a 7.2 GB ternary GGUF. Proprietary weight-level abliteration by the dealignai research team. Byte-identical to the base ternary quant everywhere except a small set of tensors that carry the refusal circuit. Drop-in replacement for the ternary base at inference — same tokenizer, same chat template, same reasoning modes, same vision projector interface.…
repacked for the q27 engine. It is Qwen3.8-27B with every projection ternary (one fp16 scale per 128 weights) in a Hadamard-rotated basis, and no MTP block. This pack is an exact re-encoding of the PTQ10 GGUF, not a requantization: every trit is stored as-is in q27's 2-bit T2G128 container, the embedding and the head as int8 (also exact), and the rotation metadata is carried verbatim so the engine rotates activations itself. Needs q27 v0.12.0 or later (the MTP pack: v0.13.0) (docs/plans/2026-09-18-bonsai2-ternary.md in the repo has the design). The pack has no MTP head, so DFlash2 is the only speculative path. The Qwen3.8 drafter packs in work against this target as-is (3.47 tokens per…
An Intel GPU optimized mirror of Credit goes to webml-community and its contributors for the original browser app and WebGPU inference implementation, and to Prism ML for Bonsai 27B. The 27-billion-parameter model uses packed 1-bit weights and runs locally on your GPU through WebGPU. Approximately 3.8 GB of model data downloads from Hugging Face; prompts and replies stay on your device. The optimizations target Intel GPUs, with performance depending on the GPU, driver and browser. Prefill and decode use fp16 activations, intermediate tensors and linear-attention recurrent state on GPUs supporting shader-f16. Weights and KV caches use fp16 where supported; the Q1 weights remain packed 1-bit…
End-to-end 1-bit language model for llama.cpp (CUDA, Metal, CPU) - 1.15 GB parameter memory (down from 16.38 GB FP16) — fits on virtually any device with a GPU - End-to-end 1-bit weights across embeddings, attention projections, MLP projections, and LM head - GGUF Q10 (g128) format with inline dequantization kernels — no FP16 materialization - Google Colab — try Bonsai in your browser, no setup required - Whitepaper — for more details on Bonsai, check out our whitepaper - Demo repo — comprehensive examples for serving, benchmarking, and integrating Bonsai - Discord — join the community for support, discussion, and updates - 1-bit kernels: llama.cpp fork (CUDA + Metal) · MLX fork (Apple…
Machine learning project for modeling UFC fight outcomes with Elo-based ratings. Project scope, requirements, and deliverables are defined in docs/scoping.md. src/data/cleaning.py cleans the raw fight- and round-level CSVs (missing values, dtypes), src/data/splitting.py splits fights chronologically for training, and src/features/engineering.py builds leakage-safe matchup and fighter-history features - everything is computed from data known before the fight being predicted. EDA lives in notebooks/ (eda.ipynb, univariatequestions.ipynb, bivariatequestions.ipynb, multivariatequestions.ipynb), including a documented red-corner recording bias in the source data that any model built on this…
static quants of https://huggingface.co/tomdacat-ai/Buddy-E4B-v2 For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants are available at https://huggingface.co/mradermacher/Buddy-E4B-v2-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/tomdacat-ai/Buddy-E4B-v2 For a convenient overview and download list, visit our model page for this model. static quants are available at https://huggingface.co/mradermacher/Buddy-E4B-v2-GGUF This is a vision model - mmproj files (if any) will be in the static repository. 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…
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.