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.
12,579Models
3,583Datasets
291Papers
7,578Publishers
12,850Sourced relationships
Updated 2026-10-23 · How the library is built
12,579 models, sorted by most downloaded.
World-action model for LAW + FastWAM, selected step-30,000 checkpoint. Use with the complete LAW-VLM-FastWAM Q1/Q2/Q3 VLM. Includes WAM weights, configuration and normalization statistics under wam/. The corresponding VLM is packaged separately. Original combined releases remain available in this repository's Git history. Code and download guide: hey-cjj/LAW. Historical RoboTwin overall success: 94.21%. These are selected historical results, not a new benchmark. Six bounded 32-GPU training save/load checks and both bounded real RoboTwin policy episodes passed before this packaging change; see release audit for scope and historical provenance limits. Tensor bytes are unchanged. LAW-authored…
World-action model for LAW + OpenWAM, selected step-120,815 checkpoint. Use with the complete LAW-VLM-OpenWAM Q1/Q2/Q3 VLM. Includes WAM weights, configuration and normalization statistics under wam/. The corresponding VLM is packaged separately. Original combined releases remain available in this repository's Git history. Code and download guide: hey-cjj/LAW. Historical RoboTwin overall success: 95.56%. These are selected historical results, not a new benchmark. Six bounded 32-GPU training save/load checks and both bounded real RoboTwin policy episodes passed before this packaging change; see release audit for scope and historical provenance limits. Tensor bytes are unchanged. LAW-authored…
Complete Qwen3-VL-2B VLM for LAW + FastWAM: Q1 planning, Q2 completion/failure assessment, and Q3 action-conditioned value estimation. Includes the frozen backbone, Q1/Q2 adapters, query embeddings and tokenizer at the repository root, plus the matching value checkpoint under q3/. Use this VLM with LAW-FastWAM. Matching training, inference, resource download and verification code: hey-cjj/LAW. Files are copied from the previously verified checkpoints without changing tensor bytes. Q2 and Q3 are the selected step-50,000 checkpoints. This packaging change does not retrain the model. The release previously passed six bounded 32-GPU two-optimizer-step training save/load checks and two bounded…
Complete Qwen3-VL-2B VLM for LAW + OpenWAM: Q1 planning, Q2 completion/failure assessment, and Q3 action-conditioned value estimation. Includes the frozen backbone, Q1/Q2 adapters, query embeddings and tokenizer at the repository root, plus the matching value checkpoint under q3/. Use this VLM with LAW-OpenWAM. Matching training, inference, resource download and verification code: hey-cjj/LAW. Files are copied from the previously verified checkpoints without changing tensor bytes. Q2 and Q3 are the selected step-50,000 checkpoints. This packaging change does not retrain the model. The release previously passed six bounded 32-GPU two-optimizer-step training save/load checks and two bounded…
This model was finetuned and converted to GGUF format using Unsloth. - LFM2.5-1.2B-Instruct.Q4KM.gguf The model's BOS token behavior was adjusted for GGUF compatibility. This was trained 2x faster with Unsloth
static quants of https://huggingface.co/FineEnvs/LFM2.5-2.6B-opencode-SFT For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants are available at https://huggingface.co/mradermacher/LFM2.5-2.6B-opencode-SFT-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…
weighted/imatrix quants of https://huggingface.co/FineEnvs/LFM2.5-2.6B-opencode-SFT For a convenient overview and download list, visit our model page for this model. static quants are available at https://huggingface.co/mradermacher/LFM2.5-2.6B-opencode-SFT-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…
GGUF quants of Blackfrost-AI/LFM2.5-24B-A2B-DERISKED-BF16. Text model. This checkpoint has no vision tower and no mmproj. Architecture is Lfm2MoeForCausalLM (lfm2moe). About 24B parameters, about 2.45B active. 40 blocks: 2 dense, 38 MoE. 64 experts, 4 routed per token. 30 short-conv blocks and 10 attention blocks. Tied embeddings. Configured context is 131072. No MTP / NextN tensors in the source checkpoint. The source is a behaviorally modified BF16 derivative of LiquidAI/LFM2.5-24B-A2B. "DERISKED" is the repository name, not a safety certification. The parent license still applies. See LICENSE. Quantized with llama.cpp llama-quantize from a BF16 GGUF. No importance matrix. Embeddings and…
Community GGUF quantizations of LiquidAI/LFM2.5-24B-A2B. If this GGUF made your day easier, a coffee would make mine. I build and test these releases myself. Your coffee helps keep me going. Thank you for supporting this work. Modification notice: The GGUF files in this repository are community-modified derivatives of the upstream BF16 checkpoint, converted to GGUF and quantized by this publisher. LFM2.5-24B-A2B is Liquid AI's text-only reasoning Mixture-of-Experts model. It has 24 billion total parameters and 2.45 billion active parameters, with 40 layers, 64 experts per MoE block, top-4 routing, and a 131,072-token context window. The upstream card lists English, Arabic, Chinese, French…
static quants of https://huggingface.co/LiquidAI/LFM2.5-24B-A2B For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants are available at https://huggingface.co/mradermacher/LFM2.5-24B-A2B-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…
A JANG bundle of LiquidAI/LFM2.5-24B-A2B: Liquid AI's 24B mixture-of-experts reasoning model with 2B active parameters (40 layers: 30 short-convolution and 10 full-attention, 64 routed experts with 4 active, two dense layers), built for on-device agents. It always thinks before answering and calls tools in Liquid's Pythonic format. 44.7 GiB of bf16 weights in 7.3 GiB. Every quantized matrix with an input Hessian was rounded with GPTQ. The Hessians come from the model's own outputs: the bf16 model wrote its thinking and answers for math, finance, code in eleven languages, terminal and coding-agent sessions (with real tool results), multi-step tool calls, networking, cybersecurity, science…
An OptiQ mixed-precision quant of LiquidAI/LFM2.5-24B-A2B, the largest model in the LFM2.5 family. It is 16.7 GB on disk, down from 47.9 GB at bf16, with a 128k context. LFM2.5-24B-A2B is a sparse mixture of experts on Liquid's hybrid backbone. Convolutional blocks alternate with full attention, so only 10 of its 40 layers keep a KV cache. Each token is routed to 4 of 64 experts. OptiQ measures each layer's sensitivity and assigns its bit-width from that. Most of the routed expert weights sit at 4-bit: 87 of the 114 fused expert projections. Attention, the routers and nearly all of the convolution blocks stay at 8-bit. Six-metric mean, the standard OptiQ eval, run in reasoning mode because…
generating better answers. This model has significant internal upgrades under user control that are "on the fly" (you set in your prompt(s) and/or API). Please read this model card carefully to get the most from it - including all the reasoning (27) that feature model suggestions ("context help") for all use cases. The Turbo Brilliance system will begin appearing in other model sizes/types shortly (IE: Qwen, Gemma, Mistral, GLM, Llama, and our fine tunes too). The Turbo Brilliance system (27 reasoning modes) vastly augments the models core performance and includes interactive help system directly connected to the model. This is like playing "Pong" vs "Entering the Matrix"... because Turbo…
static quants of https://huggingface.co/OS-Software/LFM2.5-24B-A2B-Uncensored-Heretic
weighted/imatrix quants of https://huggingface.co/LiquidAI/LFM2.5-24B-A2B For a convenient overview and download list, visit our model page for this model. static quants are available at https://huggingface.co/mradermacher/LFM2.5-24B-A2B-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…
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.