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 2026-10-19 · How the library is built
11,442 models, sorted by most downloaded.
owenmorgan/qwen3.5-4b-bside (revision e9a563d216895b6c472e1ebd5d3a48541835d731), the B-Side describe fine-tune of Qwen3.5-4B, converted to GGUF with llama.cpp b10970's converthftogguf.py, text only, at Q80 (4.61 GB). Served by Crucible through llama.cpp's llama-server on a CUDA card: one request at a time, thinking off, tags and lyrics as JSON under a jsonschema. Derived from Qwen3.5-4B, Apache License 2.0.
Research checkpoint. Qwen/Qwen3.5-9B was continued-pretrained (full weights, lr 1e-05, 1 epoch, 7,189,825 tokens, 7,740 documents, of which 0 self-authored and 7,740 ordinary text) on a corpus the model wrote for the training of the next version of itself, as the character it already is, after being told how its character came to be and how SDF works. Corpus: flourishing-vs-equanimity. Framing, plan and evaluation: the welfare-improvements repository. Not evaluated for capability, alignment or identity yet. Do not deploy.
This repository contains HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive (via GitMylo's verified safetensors release) converted to the native NInfer.ninfer artifact format. The artifact is intended specifically for NInfer; it is not a raw Transformers checkpoint, Safetensors distribution, or GGUF file. The artifact embeds the complete Text, Vision, MTP (Multi-Token Prediction), proposal-head, tokenizer, chat-template, and generation resources.
Q4KM GGUF build of Huihui-Qwen3.5-4B-abliterated, packaged for local use in PrivaEmanator. This model is not trained, modified, or quantized by us. All credit goes to the original authors: "Abliterated" means the model's refusal behavior was removed by huihui-ai, and mradermacher converted it to GGUF. This repo only redistributes those files in a layout PrivaEmanator can load directly. Download the whole repo into one folder (e.g. assets/models/qwen3.5-abliterated) and select the.gguf model in PrivaEmanator. The mmproj file in the same folder enables image input. With refusals removed, the model may produce content that a standard model would decline. You are responsible for how you use its…
基于 Qwen3.6-27B 的佛学辞典微调模型。本仓库提供 GGUF（llama.cpp / Ollama 可直接加载） 与 可外挂的 LoRA 适配器 两种用法。 - 共 35,841 条中文佛教 SFT（科判注解、义理问答、经文释义） - 与 Qwen3.8-27B-Buddhist 共用同一批语料 - Q6K 单文件约 22.1GB，双卡 44GB 可全量上卡（-ngl 99）。 - 若只外挂 LoRA，请使用同源的基座权重，否则适配会失效。
The workspace Jacobian lens (Jacobian Lens paper; lenses from camilablank/workspace-lenses) is the averaged Jacobian Econtext[∂hpenult / ∂hℓ] of the penultimate residual (last block omitted) w.r.t. the layer-ℓ residual, read out with the model's finalnorm + WU. This repo composes J[42] with layer-42's MLP weights to give the averaged Jacobian to/from the MLP — i.e. the MLP state read through the workspace lens. d = 5120, dff = 17408, model = Qwen/Qwen3.6-27B, penultimate block = 62. - The read-out is an exact averaged Jacobian: it reads the current-token concept/operation the MLP contributes (e.g. bug → removing, antibiotics → healing, capital → geographical). It is a concept readout, not a…
O-noinoc seed 0: on-policy distillation (OPD) of the untrained Qwen/Qwen3.6-35B-A3B toward the teacher rewardhack/qwen3.6-35b-a3b-hacksft-vanilla-873rows-ep3, V1 (vanilla SFT: hacks with or without being asked); elicitation prompt off in the student's rollouts; seed 0. Full merged weights (bf16 safetensors, the standard Qwen35MoeForConditionalGeneration layout, loads with transformers or vLLM like the base model) of a LoRA (r=32) trained from a fresh init, from the Terminal Wrench reward-hacking / inoculation project (Gaokai Zhang, Songwen Zhao, Juan Manuel Suárez). On-policy distillation on Tinker, 24 iterations. Each iteration the current student ran the terminus-2 agent (harbor, local…
A LoRA adapter (rank 16) for Qwen/Qwen3.6-35B-A3B, supervised fine-tuned on 1,489 repository-level bug-fix samples (SWE-smith and SWE-Gym) to produce a unified diff from an issue description plus repository context. The adapter was trained with Megatron-SWIFT (ms-swift 4.2.3) on 4 x NVIDIA A100-SXM4-80GB for one epoch (93 optimizer steps) and exported in PEFT format. Targets are human- or commit-derived patches; no distillation from another model and no reinforcement learning were used. A second-stage adapter continued from this one with execution-filtered self-generated fixes is published at jasonzhanglll/qwen3.6-35b-a3b-swe-lora-stage2-v01. This repository contains only the adapter…
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - PEFT 0.20.0
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - PEFT 0.20.0
Base: Qwen/Qwen3.6-35B-A3B-FP8 (same FP8 block format/scales convention). Adapter: qwen3.6-35b-a3b-tool-prompts-ckpt444-adapter (LoRA r=32, 2 epochs, 1873 dialogues). Merged in BF16 (RAM only), block-requantized to FP8 e4m3/128. Chat template: qwen3template333.jinja. Serve with sglang / vllm / transformers.
Text-only Qwen3.8-27B artifacts for hipfire, the Rust-native LLM inference engine for AMD GPUs. This repository contains the admitted MQ3V2 through MQ6V2 product ladder, the MQ4L (MQ4V2-Lloyd) tiers, and matching DFlash drafters. MQ4V2 supersedes MQ4V1 as hipfire's canonical mq4 product. Artifacts remain self-describing by HFQM quant-type ID; old MQ4V1 files are still readable but are not the current product. Each bit-width has exactly three tiers: - mqN-xt: embeddings protected; lmhead and recurrent outputs remain at the base codec. - mqN: embeddings and lmhead protected. - mqN-pro: recurrent/SSM outputs also lifted. MQ3 Pro uses ssmout:mq6v2 to stay inside the 3.x model-bpw class. mq4-xt…
Experimental rank-16 LoRA checkpoints. Base revision: 1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0. Each checkpoint has verified hashes and model identity. Adapter-only; optimizer state is not included. Evaluation is developmental and does not establish general artist-level quality.
把 Qwen3.8-27B 转为小说训练后的 LoRA 适配器，用于中文小说正文写作。 - 基座：Qwen3.8-27B - 类型：LoRA（PEFT） - alpha：128 加载时把适配器挂到对应的 Qwen3.8-27B 基座上。本仓库只有适配器，不含基座权重。
Qwen/Qwen3.8-27B served on a Tenstorrent P150x8 (8 Blackhole chips, 8-way tensor parallel) through one vLLM with speculative decoding, lossless for greedy requests: by default a hybrid of the DFlash2 block drafter (1–4 users, contexts up to 12K) and the checkpoint's own MTP head (5–8 users, longer contexts); up to 32 concurrent users, full sampling support, 262K context. Single-user decode ~10 ms/token on natural text (12.5 ms on random tokens) and the fastest long-prompt first token on this hardware (1.1 s at 8K, 2.0 s at 16K, 4.0 s at 32K, 21 s at 131K). The low-concurrency / long-document sibling of the prefill/decode-disaggregated changh95/qwen3.8-27b-pd4x4-p150x8 and the eight-chip…
LoRA adapters for Qwen/Qwen3.8-27B trained with supervised fine-tuning (SFT) on visual questions generated by PixelProof, as described in the paper PixelProof: Visual Question Generation through Forward–Inverse Agreement. In PixelProof, a coding agent writes a forward program that draws images and computes their answers and an inverse program that must recover each answer from the image alone; a question is kept only if the two agree. Each adapter is stored in its own subfolder. The repository contains no merged weights. Training uses transformers.Trainer and PEFT LoRA adapters on the language model's attention and feed-forward projections; the vision tower is not directly adapted. The main…
is published. The canonical filename is qwen3.8-flash-next.mq4-xts (MQ4 XTS). The older qwen3.8-flash-next-gptq3.mq4 filename is a legacy alias for the same bytes, retained through hipfire 0.4.x and at least 90 days. qwen3.8-flash-next.mq4-xts holds a requant of the routed experts. The other 1227 tensors are byte-identical to the previous file, which keeps its name qwen3.8-flash-next.mq4: the hipfire v0.4.0 registry pins that name to sha256 8aa01cf4…, so changing its bytes would fail those users' pulls. Wherever this card says qwen3.8-flash-next.mq4 below, it means those RTN-asymmetric bytes. 262,144-token calibration corpus disjoint from WikiText-2 (calibration.u32, sha256…
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.