INT8 weight-only quantization of google/gemma-4-E4B-it in the compressed-tensors format, ready for vLLM. Text, image and audio inputs are supported as in the original: only the text decoder is quantized. - Per-Layer Embeddings (embedtokensperlayer, perlayerinputgate, perlayerprojection, perlayermodelprojection) - Multimodal projections (embedvision, embedaudio) - Token embeddings and lmhead A large part of the E4B checkpoint is Per-Layer Embeddings, which stay in bf16, so the size reduction is smaller than the "8-bit" label suggests. The full recipe is in recipe.yaml. Perplexity and top-1 next-token agreement against the bf16 original on Wikipedia (wikimedia/wikipedia, dump 20231101)…
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.
11,734Models
3,323Datasets
288Papers
7,150Publishers
12,282Sourced relationships
Updated 2026-10-20 · How the library is built
11,734 models, sorted by most downloaded.
m gemma-4-E4B-it-heretic-QAT-UD-Q4KXL.gguf \ --jinja -ngl 99 -c 4096 \ --port 8001
This is a GGUF LoRA adapter, not a standalone model. It is intended for the anonymization.ner entity-extraction route in Jurilix. Apply it at strength 0.75 for that route and explicitly send strength 0 for other routes. 4b4a2c1d584be7264f87aac328a1bc739ce81b6c, file gemma-4-E4Bq40-it.gguf. The published source recipe pins upstream llama.cpp and a Gemma JSON parser fix. GPU performance or inference quality on other platforms. Start llama-server with --lora ADAPTER.gguf --lora-init-without-apply --cache-ram 0. For entity extraction, include "lora": [{"id": 0, "scale": 0.75}] in each request. For every other route, include "lora": [{"id": 0, "scale": 0}]. Disabling the RAM prompt cache is…
Google publishes the QAT Q40 model google/gemma-4-E4B-it-qat-q40-gguf as GGUF, but its multi-token-prediction (MTP) assistant only as safetensors There was no GGUF MTP head for the QAT GGUF, so this repository is that assistant converted to GGUF, nothing else: no training or fine-tuning. Use it together with google/gemma-4-E4B-it-qat-q40-gguf for speculative decoding in llama.cpp. The Google model card asks for exactly this pairing: "When using multi-token prediction (speculative decoding) with an assistant model alongside a QAT target model, the assistant model must also be a QAT checkpoint with the same precision." llama.cpp at commit 0c1e570 (Gemma4AssistantForCausalLM → GGUF…
gemma-4-e2b-it-OptiQ-4bit turned into a decision model with optiq lora train --decision: a LoRA on the backbone and a new joint schema head that scores noul, choice and score questions in one pass. It runs on Apple Silicon through MLX and OptiQ (optiq serve exposes /v1/systemone). Scored on the full 400-case test split (2,000 decisions) with the benchmark's own metrics. Latency is one request per case with all five questions, on an Apple M3 Max. This model was fitted on the benchmark's own train split and nothing else: 1,080 records, 3 epochs, LoRA rank 16. The test cases are disjoint from it, but they come from the same four workflows, so expect less on decisions of a different kind. The…
Web-optimized gemma-4-E2B-it LiteRT-LM bundles for browser (WebGPU) execution, built with the official conversion pipeline (exportvit, convertermain, litertlmbuildercli). - Multi-signature visionencoder (vision70, vision140, vision280, vision560, vision1120) exported via //thirdparty/odml/generative/modules/gemini/export:exportvit with QAT Int8 weight recovery and query-chunked attention (maxquerychunksize = 630, $k=16$ at vision1120). - Artisan decoder visiontokensnum: 1121 (tokensnum = 1120).
Web-optimized gemma-4-E4B-it LiteRT-LM bundles for browser (WebGPU) execution, built with the official conversion pipeline (exportvit, convertermain, litertlmbuildercli). - Multi-signature visionencoder (vision70, vision140, vision280, vision560, vision1120) exported via //thirdparty/odml/generative/modules/gemini/export:exportvit with QAT Int8 weight recovery and query-chunked attention (maxquerychunksize = 630, $k=16$ at vision1120). - Artisan decoder visiontokensnum: 1121 (tokensnum = 1120).
This model is a fine-tuned version of google/gemma-4-E2B. It has been trained using TRL. This model was trained with SFT.
This model is a fine-tuned version of google/gemma-4-12B-it. It has been trained using TRL. This model was trained with SFT.
This model is a fine-tuned version of google/gemma-4-12B-it. It has been trained using TRL. This model was trained with SFT.
This model is a fine-tuned version of unsloth/gemma-4-26B-A4B-it. It has been trained using TRL. This model was trained with SFT.
This model is a fine-tuned version of unsloth/gemma-4-26B-A4B-it. It has been trained using TRL. This model was trained with SFT.
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.