This repository contains the model-only checkpoint saved at 30,000 training steps. The files at the repository root are the original contents of checkpoint-30000. Full model and processor settings are in config.json, processorconfig.json, and experimentcfg/. The training run did not include an evaluation. Source checkpoint: outputs/moeforcetransformertuningobs2h1020260926223332/usbk6s1e4f384xformer/usb/moe/checkpoint-30000.
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.
This repository contains the model-only checkpoint saved at 30,000 training steps. The files at the repository root are the original contents of checkpoint-30000. Full model and processor settings are in config.json, processorconfig.json, and experimentcfg/. The training run did not include an evaluation. Source checkpoint: outputs/moeobs2h10fourtasks20260926191812/pair67/vasev6/moe/checkpoint-30000.
This repository contains the model-only checkpoint saved at 30,000 training steps. The files at the repository root are the original contents of checkpoint-30000. Full model and processor settings are in config.json, processorconfig.json, and experimentcfg/. The training run did not include an evaluation. Source checkpoint: outputs/moeforcetransformertuningobs2h1020260926223332/vasev6k12s1e6f384xformer/vasev6/moe/checkpoint-30000.
This repository contains the model-only checkpoint saved at 30,000 training steps. The files at the repository root are the original contents of checkpoint-30000. Full model and processor settings are in config.json, processorconfig.json, and experimentcfg/. The training run did not include an evaluation. Source checkpoint: outputs/moeobs2h10fourtasks20260926191812/pair45/weightsorting/moe/checkpoint-30000.
This repository contains the model-only checkpoint saved at 30,000 training steps. The files at the repository root are the original contents of checkpoint-30000. Full model and processor settings are in config.json, processorconfig.json, and experimentcfg/. The training run did not include an evaluation. Source checkpoint: outputs/moeobs2h10fourtasks20260926191812/pair45/whiteboardv9/moe/checkpoint-30000.
This repository contains the model-only checkpoint saved at 30,000 training steps. The files at the repository root are the original contents of checkpoint-30000. Full model and processor settings are in config.json, processorconfig.json, and experimentcfg/. The training run did not include an evaluation. Source checkpoint: outputs/moeforcetransformertuningobs2h1020260926223332/whiteboardv9k8s1e6f384xformer/whiteboardv9/moe/checkpoint-30000.
This public repository collects one USB-B no-force baseline and eight independent force MoE experiments (Q02–Q09). Each run trains for 30,000 optimizer steps. Only final checkpoints that pass local validation and remote integrity verification are listed as uploaded. The uploader watches the remaining runs and adds them here. Each checkpoint directory includes complete indexed Safetensors weights, model configuration, processor files, normalization statistics, and embodiment information. The MoE checkpoints use a shared frozen-weight shard plus an experiment-specific trainable-weight shard; the index references both files in the same directory. Load each checkpoint with the ForceBenchmark…
This repository contains the complete GRADE model, paper ablations, and baselines: 19 model checkpoint files plus one auxiliary TAESD weight file (20.safetensors files in total). It also includes the inference and metric code and the saved camera-ready quantitative results. The full GRADE model uses the radar, diffusion, and ControlNet checkpoints in checkpoints/grade/. - E1 — saved-result reproduction: regenerate the quantitative tables and figures from the supplied camera-ready CSVs and auxiliary evaluation data. This requires no inference or dataset download. - E2 — local reproduction: run inference on the released evaluation data, compute 2D/3D metrics, then regenerate the quantitative…
Gander-Omni/Gander, release Gander-v63-Unit8 on MiniCPM-o 4.5, with refusal behaviour reduced by abliteration of the Thinker's language tower. It is BF16 and keeps upstream's layout, thinker/ and talker/, so it drops into the Gander runtime the same way as the upstream release. An NVFP4 build is at Only the Thinker's language tower (llm., Qwen3-8B shape, 36 layers). The Thinker's vision tower, audio tower, resampler and audio projection are upstream's, unmodified. So are the Talker (talker/) and its token2wav assets. - 72 matrices were changed: selfattn.oproj and mlp.downproj in all 36 layers. - The largest relative change is ‖ΔW‖/‖W‖ = 0.135. - The language tower was extracted as a…
The Thinker of justsumguy/Gander-ablated, quantised with NVIDIA ModelOpt 0.46.1, plus the unmodified BF16 Talker. The Thinker is 7.2 GB and the Talker 0.7 GB. The abliteration details and numbers are on the BF16 page. In short: heretic ARA branch, ARA-LoRA rank 128, trial 4, refusals 98 → 7 of 100, KL 0.128 on recheck, no healing applied. talker/ is BF16 and identical to the BF16 repository's. - llm calibration: 256 samples × 512 tokens of tatsu-lab/alpaca (shuffled, seed 0), run through the extracted text tower. Mean NLL on 8 calibration chats: BF16 4.335, NVFP4 fake-quant 4.408 (+0.073). - vpm calibration: 80 images from johnowhitaker/imagenette2-320. Three quarters were unsliced; one…
Unlike incomplete GGUF uploads, this repository provides the full 11-quantization spectrum (from high-precision F16 down to lightweight Q2K) of the abliterated Gemma-3-27b-it model. Choose the exact fit for your VRAM/RAM constraints without sacrificing reasoning capabilities. This is the integral and complete collection of quantizations in GGUF format for the gemma-3-27b-it-abliterated model, prepared locally for use with llama.cpp, Ollama, LM Studio, or any application compatible with multimodal models. This model is an uncensored version based on Google's powerful Gemma 3 27B multimodal engine. Being significantly more resistant to neutralization than previous architectures, it was…
A code-focused finetune of llmfan46/gemma-4-E2B-it-ultra-uncensored-heretic (Gemma 4 E2B, ~4.6B effective) built specifically for front-end development (React, TypeScript, HTML/CSS) and general Python scripting. Built on an uncensored base, so it just answers the question—no lectures attached. It’s a small model, trained on a single consumer GPU. It writes React components, fixes CSS grid layouts, and won't judge your useEffect dependencies. Measured with lm-evaluation-harness (greedy decoding, temp 0.0, seed 0). Same harness, same conditions for both models. Note: The base model scores higher on pure, edge-case Python algorithmic logic. Hiding it would be weird. This model intentionally…
A variant of Google's Gemma 4 E2B-it fine-tuned model, quantized for the LiteRT-LM browser runtime (int4/int2 weights, int8 static activation quantization). The abliteration edit from the GGUF model was reverse-engineered as a rank-1 direction per matrix layer. About 35% of the edit survives quantization to Google's int4/int2 grid with per-channel scales (mostly in attention output and FFN matrices; less in int2 layers). The result is a model with substantially weakened or removed refusals while maintaining similar generation quality. The model has minimal resistance to requests regardless of framing or content type. It is not suitable for applications requiring strong safety guardrails.…
static quants of https://huggingface.co/Nimbz/Gemma-4-Orthia-31B
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.