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 2026-10-23 · How the library is built
12,579 models, sorted by most downloaded.
On a laptop running Debian 13 Linux, with an Intel Core Ultra 9 185H, its integrated Arc GPU and 32 GB of memory, Janas-LLM reads a prompt at 939 tok/s and writes at 130 tok/s: llama.cpp, on the same laptop, 670 and 45. Measured on 9-11 October 2026: llama-bench -p 1024 -n 16 and janas-bench --prompt 1024 --gen 16, both at their best configuration. On other machines the figures will differ. Details: Janas README. - Debian 13 (trixie) Linux, x86-64, kernel 6.12.107 - its integrated Intel Arc GPU, through the Vulkan driver of Mesa 26.1.6 - 32 GB of DDR5-5600 memory - a 1 TB NVMe SSD, about 5.7 GB/s reading - llama.cpp build 2b18470 (18 September 2026), Vulkan backend These are the model's…
GGUF quantization of orlandorubino/Qwen3-1.7B-heretic (a finetune of Qwen/Qwen3-1.7B), converted with llama.cpp's converthftogguf.py. Works with llama.cpp, Jan, LM Studio, Ollama and other GGUF runtimes.
An ahead-of-time compiled.litertlm of Qwen/Qwen3-1.7B for the Qualcomm Hexagon NPU (v79, SM8750), made for the Android app Chiko - Local AI Hub. litert-torch 0.9.4 generative/exporthf/experimental/npuexport with ai-edge-litert 2.2.0 and the Qualcomm AI Runtime 2.47.0.260601 compiler plugin, calibrated on Japanese chat-formatted prompts. The prefill/decode model is entirely DISPATCHOP (runs on the NPU); the embedder and KV-cache updates run on the CPU, the same layout as Google's official NPU builds. It needs the LiteRT Qualcomm dispatch library and QNN runtime libraries on the device. The quantized model was run on a PC CPU with litert-torch's executor and scored with a 30-question Japanese…
Continued LoRA fine-tune of Qwen3-1.7B-teacher-note-severity (itself a LoRA of Qwen/Qwen3-1.7B, 32K context). v2 adds a location field. Given a teacher note (or a running log), it outputs: {"category": "commendation|misbehavior|academicconcern", "location": "inclass|outsideclass", "severity":, "escalate": } Commendations are negative; routine notes 5-55; severity >= 60 escalates to admin. Trained on synthetic data: jeremierostan/teacher-notes-severity-v2 (continues v1 training, LR 1e-4, 2 epochs).
GGUF builds of jeremierostan/Qwen3-1.7B-teacher-note-severity-v2, which adds an inclass / outsideclass location field to the v1 severity model - Qwen3-1.7B-teacher-note-severity-v2-f16.gguf (3.4 GB) — full precision - Qwen3-1.7B-teacher-note-severity-v2-q80.gguf (1.8 GB) — recommended; near-identical quality, half the size Given a teacher note (or a running log of notes), the model replies with a single JSON object: Commendations score negative; routine notes 5–55; severity >= 60 means escalate to admin (escalate is set exactly when severity >= 60, across all categories). 1. In LM Studio, search this repo id (jeremierostan/Qwen3-1.7B-teacher-note-severity-v2-GGUF) and download the q80 file…
Over the past three months, we have continued to scale the thinking capability of Qwen3-235B-A22B, improving both the quality and depth of reasoning. We are pleased to introduce Qwen3-235B-A22B-Thinking-2507, featuring the following key enhancements: - Significantly improved performance on reasoning tasks, including logical reasoning, mathematics, science, coding, and academic benchmarks that typically require human expertise — achieving state-of-the-art results among open-source thinking models. - Markedly better general capabilities, such as instruction following, tool usage, text generation, and alignment with human preferences. - Enhanced 256K long-context understanding capabilities.…
On a laptop running Debian 13 Linux, with an Intel Core Ultra 9 185H, its integrated Arc GPU and 32 GB of memory, Janas-LLM reads a prompt at 135 tok/s and writes at 32 tok/s: llama.cpp, on the same laptop, 122 and 15. The other files of this repository, measured the same way: The 3-bit file reads a prompt slower than llama.cpp: its Q3K weights do not go to the GPU's fast prompt yet. It writes three times as fast. Measured on 9-11 October 2026: llama-bench -p 1024 -n 16 and janas-bench --prompt 1024 --gen 16, both at their best configuration. On other machines the figures will differ. Details: Janas README. - Debian 13 (trixie) Linux, x86-64, kernel 6.12.107 - its integrated Intel Arc GPU…
This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.
This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.
This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.
This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.
This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.
This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.
static quants of https://huggingface.co/WasamiKirua/Qwen3-4B-Alucard 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…
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.