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.
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 0.19.1
Glade is a native Swift library for on-device speech inference on Apple silicon. This repository supplies converted model assets and configuration for Glade's model-specific host runtime. Glade's runtime source is currently private. Glade conversion of Qwen3-ASR-1.7B by the Qwen Team, Alibaba Cloud, at source revision 7278e1e70fe206f11671096ffdd38061171dd6e5. The converted weights retain Apache-2.0 licensing; see LICENSE and NOTICE. This conversion is not endorsed by the upstream authors. This repository contains one offline transcription bundle, approximately 2.68 GB, using 30-second chunks and up to eight independent decoder lanes. It prefers ANE for both the audio encoder and…
A Windows x64 CPU package for offline transcription with sherpa-onnx. The decoder has a statically exported 4096-position KV cache. It uses a mixed INT8/FP32 decoder and retains the matching FP16 encoder and convolution frontend from the pinned sherpa-compatible ONNX export. - maxtotallen: 4096; tested maxnewtokens: 1024 The encoder is kept FP16 because the compatible INT8 encoder from a separate 512-context export substantially reduced Japanese recognition quality in a controlled comparison. On the same FLEURS Japanese sample, the mixed decoder with the FP16 encoder measured 8.2% character error rate (CER), compared with 5.5% for the all-FP16 source and 22.7% when using that separate INT8…
Glade is a native Swift library for on-device speech inference on Apple silicon. This repository supplies converted model assets and configuration for Glade's model-specific host runtime. Glade's runtime source is currently private. Glade conversion of Qwen3 ForcedAligner, source revision c07281df297b9905d24a508279258cccf987a064. The upstream model and converted weights use Apache License 2.0. The complete checkpoint has approximately 918 million parameters; the 0.6B name describes its text backbone. This model predicts timestamps for supplied words. It does not recognize or replace a transcript. Requires physical Apple silicon with macOS 27 or iOS 27, Core AI APIs, and Glade's…
This model was finetuned and converted to GGUF format using Unsloth. - Qwen3.5-9B.Q4KM.gguf - Qwen3.5-9B.F16-mmproj.gguf This was trained 2x faster with Unsloth
Encrypted experimental release payload for a custom Talker/MTP LoRA layer over Qwen3-Omni. This repository payload contains encrypted step96 adapter artifacts only: - encrypted/talkermtplora.safetensors.aes256gcm - encrypted/talkermtplora.safetensors.aes256gcm.nonce - encrypted/talkermtplora.safetensors.aes256gcm.tag - decryptlocal.ps1 - DECRYPTGUIDE.md - encryptiontestreport.json - RELEASEMANIFEST.sha256.txt It does not include plaintext weights, the decryption key, private local notes, restored test outputs, temporary failure-test outputs, or the full training project. This release is for experimental review and verification only. Commercial use is not permitted without explicit written…
52 complete FP32 checkpoints for Qwen3-1.7B PG-OPD with Qwen3-4B-Instruct-2507 teacher. Full seeds 0/1/2/3 at steps 5/10/15/20; Fisher/Random q=0.5%, 1%, 5% at step 20, Random mask seeds 0/1. Download an entire runs/ /checkpoint- / directory (weights, config, tokenizer). Optimizer states are not included. Checkpoint files were preserved without reupload. All 17 Test1 sets and the remaining research records are in the final public dataset snapshot: https://huggingface.co/datasets/yufanzh/qwen3-opd-records-20260926/tree/e60404a2dfcebf402da94441f9a1d831d22fddd3 Current HEAD contains checkpoints plus README/catalog. Earlier mixed-archive history and all local originals are preserved. The…
First-party Nile Academy conversion of the official Qwen checkpoint at fd4b254389122332181a7c3db7f27e918eec64e3. This is a derivative ONNX artifact, not an ONNX release published by Qwen. It contains data only; Python is not required by BookAlive. The fp32 pack includes a speaker encoder, talker with an explicit KV cache, a complete code-predictor frame, speech decoder, embedding tables, tokenizer and publisher licence. BookAlive reuses its Qwen VoiceDesign generation implementation for the Base talker, predictor and decoder. The source implementation is pinned at 022e286b98fbec7e1e916cb940cdf532cd9f488e. The current adapter uses x-vector-only reference cloning. It supports ten languages…
This qwen3vl model was trained 2x faster with Unsloth and Huggingface's TRL library.
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
This model is a fine-tuned version of unsloth/qwen3-vl-8b-instruct-unsloth-bnb-4bit. It has been trained using TRL. This model was trained with SFT.
Full fine-tune of Qwen/Qwen3-VL-8B-Instruct (revision 0c351dd) for the box-conditioned variant of the deleafing cut-point task: the input is one robot head-camera frame (848x408 RGB) with its aligned depth map (metres, fed as a rendered second image) and the bounding box of the target petiole; the output is the nominal cut point 9 mm along that petiole from its junction with the main stem. The model does not choose the target. Compared with the box+point models in this account (qwen3-vl-8b-tomato-cutpoint-bp-, which find the petiole themselves), this one measures localization given identity. Answer: {"cutpointuv":[x,y]} in normalized [0,1000) coordinates of the original 848x408 frame (2…
This model is a fine-tuned version of Qwen/Qwen3.5-0.8B. It has been trained using TRL. This model was trained with SFT. - PEFT 0.21.0
Qwen/Qwen3.5-0.8B fully fine-tuned (no LoRA) on FreedomIntelligence/medical-o1-reasoning-SFT (en). Only the MLP blocks of layers [0, 1, 2, 3, 4] were trained; everything else is frozen. Checkpoint: best.pt. Split 80/10/10, 10 epochs, lr 1e-05.
This model is a fine-tuned version of /mnt/shared-storage-user/mineru2-shared/niujunbo/ldy/models/Qwen3.5-35B-A3B-Instruct on the merged8083ulogocohqwen35 dataset. The following hyperparameters were used during training: - learningrate: 5e-05 - trainbatchsize: 1 - evalbatchsize: 8 - distributedtype: multi-GPU - numdevices: 8 - gradientaccumulationsteps: 8 - totaltrainbatchsize: 64 - totalevalbatchsize: 64 - lrschedulertype: cosine - lrschedulerwarmupsteps: 0.1 - numepochs: 1.0 - Transformers 5.6.0 - Pytorch 2.10.0+cu128 - Datasets 4.0.0 - Tokenizers 0.22.2
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.