# Models, Page 220 of 525
Source: https://savrn.com/models/page/220
Markdown alternate of the page above; the site index is https://savrn.com/llms.txt

---

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](https://savrn.com/model-hub/methodology)

## Filter Models

Task

- [Text generation1,548](https://savrn.com/models?task=Text+generation)
- [Image and text to text577](https://savrn.com/models?task=Image+and+text+to+text)
- [Feature extraction398](https://savrn.com/models?task=Feature+extraction)
- [Robotics398](https://savrn.com/models?task=Robotics)
- [Text classification331](https://savrn.com/models?task=Text+classification)
- [Text to image232](https://savrn.com/models?task=Text+to+image)
- [Speech recognition187](https://savrn.com/models?task=Speech+recognition)
- [Text to speech145](https://savrn.com/models?task=Text+to+speech)
- [Image classification139](https://savrn.com/models?task=Image+classification)
- [Audio classification130](https://savrn.com/models?task=Audio+classification)
- [Sentence similarity103](https://savrn.com/models?task=Sentence+similarity)
- [Reinforcement learning100](https://savrn.com/models?task=Reinforcement+learning)
- [Token classification100](https://savrn.com/models?task=Token+classification)
- [Zero-shot classification94](https://savrn.com/models?task=Zero-shot+classification)
- [Image segmentation90](https://savrn.com/models?task=Image+segmentation)
- [Object detection86](https://savrn.com/models?task=Object+detection)
- [Translation80](https://savrn.com/models?task=Translation)
- [Any to any79](https://savrn.com/models?task=Any+to+any)
- [Question answering73](https://savrn.com/models?task=Question+answering)
- [Fill mask69](https://savrn.com/models?task=Fill+mask)
- [Time series forecasting64](https://savrn.com/models?task=Time+series+forecasting)
- [Video classification61](https://savrn.com/models?task=Video+classification)
- [Image to text60](https://savrn.com/models?task=Image+to+text)
- [Text to video55](https://savrn.com/models?task=Text+to+video)

Library

- [transformers3,001](https://savrn.com/models?library=transformers)
- [peft367](https://savrn.com/models?library=peft)
- [diffusers206](https://savrn.com/models?library=diffusers)
- [pytorch198](https://savrn.com/models?library=pytorch)
- [gguf187](https://savrn.com/models?library=gguf)
- [mlx169](https://savrn.com/models?library=mlx)
- [lerobot152](https://savrn.com/models?library=lerobot)
- [sentence-transformers139](https://savrn.com/models?library=sentence-transformers)
- [timm49](https://savrn.com/models?library=timm)
- [llama.cpp46](https://savrn.com/models?library=llama.cpp)
- [transformers.js45](https://savrn.com/models?library=transformers.js)
- [flaxspeaker44](https://savrn.com/models?library=flaxspeaker)
- [diffusion-single-file40](https://savrn.com/models?library=diffusion-single-file)
- [onnx40](https://savrn.com/models?library=onnx)
- [vllm40](https://savrn.com/models?library=vllm)
- [openpi35](https://savrn.com/models?library=openpi)
- [minimax-h328](https://savrn.com/models?library=minimax-h3)
- [ultralytics24](https://savrn.com/models?library=ultralytics)
- [PaddleOCR22](https://savrn.com/models?library=PaddleOCR)
- [coreml22](https://savrn.com/models?library=coreml)
- [exllamav322](https://savrn.com/models?library=exllamav3)
- [openvino20](https://savrn.com/models?library=openvino)
- [litert17](https://savrn.com/models?library=litert)
- [litert-lm16](https://savrn.com/models?library=litert-lm)

Modality

- [Other7,212](https://savrn.com/models?modality=Other)
- [Text2,838](https://savrn.com/models?modality=Text)
- [Image and text637](https://savrn.com/models?modality=Image+and+text)
- [Image598](https://savrn.com/models?modality=Image)
- [Control498](https://savrn.com/models?modality=Control)
- [Audio481](https://savrn.com/models?modality=Audio)
- [Video116](https://savrn.com/models?modality=Video)
- [Multimodal79](https://savrn.com/models?modality=Multimodal)
- [Time series64](https://savrn.com/models?modality=Time+series)
- [Tabular56](https://savrn.com/models?modality=Tabular)

License

- [apache-2.03,344](https://savrn.com/models?license=apache-2.0)
- [mit1,319](https://savrn.com/models?license=mit)
- [other796](https://savrn.com/models?license=other)
- [cc-by-nc-4.0213](https://savrn.com/models?license=cc-by-nc-4.0)
- [cc-by-4.0164](https://savrn.com/models?license=cc-by-4.0)
- [bsd-3-clause108](https://savrn.com/models?license=bsd-3-clause)
- [gemma63](https://savrn.com/models?license=gemma)
- [cc-by-nc-sa-4.055](https://savrn.com/models?license=cc-by-nc-sa-4.0)
- [llama3.240](https://savrn.com/models?license=llama3.2)
- [unknown33](https://savrn.com/models?license=unknown)
- [agpl-3.032](https://savrn.com/models?license=agpl-3.0)
- [llama3.128](https://savrn.com/models?license=llama3.1)
- [cc-by-sa-4.020](https://savrn.com/models?license=cc-by-sa-4.0)
- [gpl-3.020](https://savrn.com/models?license=gpl-3.0)
- [openrail++17](https://savrn.com/models?license=openrail%2B%2B)
- [creativeml-openrail-m15](https://savrn.com/models?license=creativeml-openrail-m)
- [openmdw-1.115](https://savrn.com/models?license=openmdw-1.1)
- [cc-by-nc-nd-4.014](https://savrn.com/models?license=cc-by-nc-nd-4.0)
- [llama314](https://savrn.com/models?license=llama3)
- [openrail14](https://savrn.com/models?license=openrail)
- [llama28](https://savrn.com/models?license=llama2)
- [afl-3.07](https://savrn.com/models?license=afl-3.0)
- [osl-3.06](https://savrn.com/models?license=osl-3.0)
- [cc0-1.04](https://savrn.com/models?license=cc0-1.0)

Access

- [Open weights12,153](https://savrn.com/models?access=open_access)
- [Access requested at publisher426](https://savrn.com/models?access=gated)

Publisher

- [Team Mradermacher328](https://savrn.com/models?publisher=mradermacher)
- [Yurun Yuan115](https://savrn.com/models?publisher=ryanyr)
- [RunningHub.ai105](https://savrn.com/models?publisher=runninghubai)
- [Qwen91](https://savrn.com/models?publisher=qwen)
- [Jenny Wilson85](https://savrn.com/models?publisher=jenny08311)
- [Jessen Pu77](https://savrn.com/models?publisher=putty77)
- [RKNNAI73](https://savrn.com/models?publisher=rknnai)
- [AI at Meta72](https://savrn.com/models?publisher=facebook)
- [Convergent Intelligence66](https://savrn.com/models?publisher=reaperdoesntknow)
- [Yurun Yuan65](https://savrn.com/models?publisher=yurunyyr)
- [Google64](https://savrn.com/models?publisher=google)
- [Yurun Yuan62](https://savrn.com/models?publisher=yuruny)
- [Firza Hadzami61](https://savrn.com/models?publisher=firzahdzm)
- [Zeyuan Yang59](https://savrn.com/models?publisher=miiche)
- [Yurun Yuan58](https://savrn.com/models?publisher=yyuan244)
- [Yanggangu57](https://savrn.com/models?publisher=yanggangu)
- [Hongao56](https://savrn.com/models?publisher=cisco1963)
- [Christopher Subia-Waud55](https://savrn.com/models?publisher=cwaud)
- [Francesca Padovani53](https://savrn.com/models?publisher=francesca9805)
- [Khazzz1c53](https://savrn.com/models?publisher=khazic)
- [Alfred Smith52](https://savrn.com/models?publisher=alfred8995)
- [Szekely52](https://savrn.com/models?publisher=attila115)
- [NVIDIA50](https://savrn.com/models?publisher=nvidia)
- [Wang49](https://savrn.com/models?publisher=davidwdw)

[Most downloaded](https://savrn.com/models?sort=downloads)[Most liked](https://savrn.com/models?sort=likes)[Recently updated](https://savrn.com/models?sort=updated)[Name](https://savrn.com/models?sort=name)[Largest](https://savrn.com/models?sort=params)

12,579 models, sorted by most downloaded.

Model · Text generation

### [Qwen3.6-35B-A3B-MoEGraded](https://savrn.com/models/qwen3-6-35b-a3b-moegraded)

[Zlwa](https://savrn.com/model-publishers/e-stick)

Qwen3.6-35B-A3B · every expert gets the bit width it earns English · 简体中文 A MoE model doesn't activate all of its experts equally often. Some get called constantly, some barely at all — yet a normal quantization gives every expert the same bit width anyway. So the routed experts get quantized by how often they actually fire in real tasks: high frequency keeps more bits, low frequency gets squeezed. Noise on this corpus runs ±0.029, so honestly these two measure the same. The difference is what the middle and cold tiers get to keep. 14 chunks × 512 tokens, -t 20, same machine throughout: Balanced dipping under F16 isn't a real win — 0.002 is well inside the noise. The part worth looking at…

Open weights apache-2.0

[View model](https://savrn.com/models/qwen3-6-35b-a3b-moegraded)

Model · Text generation

### [Qwen3.6-35B-A3B-Q6dense-GGUF](https://savrn.com/models/qwen3-6-35b-a3b-q6dense-gguf)

[Ligamentexceed](https://savrn.com/model-publishers/ligamentexceed)

A GGUF of Qwen/Qwen3.6-35B-A3B with higher-precision dense weights and the model's native MTP (multi-token prediction) block, for fast speculative decoding. File: Qwen3.6-35B-A3B-Q6dense.gguf, 22,388,168,960 bytes, SHA-256 842ed2bf58034c2f4856239d04de57acec27183ef4012e469d1a423a8de23108. On AMD Strix Halo (gfx1151) with gufo, the Q6K dense weights gave the same task quality as UD-Q4KXL and were faster with MTP than other dense quantizations we tried. Greedy next-token agreement at revision 5bc3e238d916f48a861bac2f8a1990a0e9b7e98d. Quantized with llama.cpp b11069 (commit 68d9053a). q6dense.types in this repo sets the type of Apache-2.0, as the original model. This is a modified (requantized)…

Open weights apache-2.0

[View model](https://savrn.com/models/qwen3-6-35b-a3b-q6dense-gguf)

Model

### [Qwen3.6-35B-A3B-Sydney](https://savrn.com/models/qwen3-6-35b-a3b-sydney)

[Evidence Wannary](https://savrn.com/model-publishers/evidence114)

Open weights

[View model](https://savrn.com/models/qwen3-6-35b-a3b-sydney)

Model · Text generation

### [Qwen3.6-35B-A3B-TT-Mixed-BFP4-BFP8-P150](https://savrn.com/models/qwen3-6-35b-a3b-tt-mixed-bfp4-bfp8-p150)

[Lotto](https://savrn.com/model-publishers/lottolabs)

A hardware-specific, text-only checkpoint and custom runtime derived from Qwen/Qwen3.6-35B-A3B, revision 995ad96eacd98c81ed38be0c5b274b04031597b0, for one Tenstorrent Blackhole P150. This is a community experimental release by Lottolabs, not an official Qwen or Tenstorrent release. It is not GGUF, AWQ, an AutoGPTQ/GPTQModel int4 checkpoint, bitsandbytes, NVFP4, or an ordinary Transformers checkpoint. transformers.frompretrained() and hosted Inference Providers are not supported launch paths. The vision encoder of the upstream model is not included: the server accepts text only. - Checkpoint (checkpoint/, 21.7 GB, manifest sha256 439096088c8b…): - routed experts (256 per layer × 40 layers)…

Open weights apache-2.0

[View model](https://savrn.com/models/qwen3-6-35b-a3b-tt-mixed-bfp4-bfp8-p150)

Model

### [Qwen3.6-35B-A3B-harness-expert](https://savrn.com/models/qwen3-6-35b-a3b-harness-expert)

[Batu Tonaroglu](https://savrn.com/model-publishers/batukhan84)

Open weights transformers

[View model](https://savrn.com/models/qwen3-6-35b-a3b-harness-expert)

Model · Text generation

### [Qwen3.6-35B-A3B-lododo-Distill-v1.0-GGUF](https://savrn.com/models/qwen3-6-35b-a3b-lododo-distill-v1-0-gguf)

[Lododo.org](https://savrn.com/model-publishers/lododoai)

Open weights apache-2.0 transformers

[View model](https://savrn.com/models/qwen3-6-35b-a3b-lododo-distill-v1-0-gguf)

Model

### [Qwen3.6-35B-A3B-oQ4e-fp16-mtp](https://savrn.com/models/qwen3-6-35b-a3b-oq4e-fp16-mtp)

[Harish Kothandaraman](https://savrn.com/model-publishers/hsk0201)

Text and vision retained Quantised using oMLX v0.5.0.rc1 OQ Enhanced quantization (oQe) iMatrix MTP Heads retained FP16 is fastest on M1/M2, but this can work on all MLX inferencing systems This model is using the LATEST FROGGERIC chat template upgrade (Fixed jinja chat templates for Qwen 3.5 & 3.6 (v21))

Open weights apache-2.0 36B parameters 262,144 tokens mlx

[View model](https://savrn.com/models/qwen3-6-35b-a3b-oq4e-fp16-mtp)

Model · Image and text to text

### [Qwen3.6-35B-A3B-oQ6e-mtp](https://savrn.com/models/qwen3-6-35b-a3b-oq6e-mtp)

[Chris Derby](https://savrn.com/model-publishers/thederby)

oQ6e mixed-precision MLX quantization of Qwen/Qwen3.6-35B-A3B, made with oMLX oQe (v0.7.1.dev1). This is the bf16 build. The multi-token-prediction (MTP) head is kept and the vision tower is included. The same family at every bit width and dtype (this repo in bold): Which dtype? bf16 (no suffix) is the default. fp16 builds store the language model's non-quantized weights and the quantization scales as float16 instead of bfloat16. They are marginally closer to the original at every level. oMLX notes that float16 can give faster prefill on M1/M2, which lack native bfloat16. They are about 0.9 GB larger because the vision tower is kept in float32; vision quality was not measured. How these…

Open weights apache-2.0 36B parameters 262,144 tokens mlx

[View model](https://savrn.com/models/qwen3-6-35b-a3b-oq6e-mtp)

Model

### [Qwen3.6-35B-A3B-oQ8e-fp16-mtp](https://savrn.com/models/qwen3-6-35b-a3b-oq8e-fp16-mtp)

[Chris Derby](https://savrn.com/model-publishers/thederby)

Open weights

[View model](https://savrn.com/models/qwen3-6-35b-a3b-oq8e-fp16-mtp)

Model

### [Qwen3.6-35b-lora](https://savrn.com/models/qwen3-6-35b-lora)

[Ruixiao Yang](https://savrn.com/model-publishers/ruixiao)

This repository contains the preserved LoRA adapter checkpoint, tokenizer and native chat template. It requires the original base model Qwen/Qwen3.6-35B-A3B at revision 995ad96eacd98c81ed38be0c5b274b04031597b0; it is not a standalone merged model. Adapter SHA256: 420b8682d0e042f110f521a28a6f85e95491b343d1fb73bafb669e3b0004db91. Size: 130,065,504 bytes; 380 FP32 tensors / 32,501,760 parameters. This is the final step-94 V6 adapter. Fresh original base; attention-only LoRA rank 32, alpha 32, dropout 0; BF16 base and FP32 adapter. Experts, routers, vision, embeddings and LM head were frozen. One epoch, 94 optimizer updates, LR 1e-5, microbatch 1, accumulation 16, warmup ratio 0.05, weight…

Open weights apache-2.0 peft

[View model](https://savrn.com/models/qwen3-6-35b-lora)

Model

### [Qwen3.6-35b-nca](https://savrn.com/models/qwen3-6-35b-nca)

[Ruixiao Yang](https://savrn.com/model-publishers/ruixiao)

This repository contains the preserved LoRA adapter checkpoint, tokenizer and native chat template. It requires the original base model Qwen/Qwen3.6-35B-A3B at revision 995ad96eacd98c81ed38be0c5b274b04031597b0; it is not a standalone merged model. Adapter SHA256: 9bb6cc8bdd71bd126112a1e9b6965352b509f3ca6e8938be3276757d81edeaa8. Size: 130,065,504 bytes; 380 FP32 tensors / 32,501,760 parameters. The NCA adapter already includes the continued V6 weights: apply it directly to the original base, do not stack it on top of V6. Continued a copy of V6 SFT with NCApair preference loss (not standard DPO). The reference was the exact frozen V6 adapter. One epoch of 184 training pairs (149 coding, 35…

Open weights apache-2.0 peft

[View model](https://savrn.com/models/qwen3-6-35b-nca)

Model · Image and text to text

### [Qwen3.8-27B](https://savrn.com/models/qwen3-8-27b-2)

[Kyle Thomas](https://savrn.com/model-publishers/xyrwex)

Following the widespread community adoption of the Qwen3.5 and Qwen3.6 series, we are pleased to introduce Qwen3.8, the most capable generation in the Qwen open-model family to date. Built on the architectural foundation of Qwen3.5, Qwen3.8 delivers substantial gains across coding, professional work, research, and long-horizon agentic tasks. Qwen3.8-27B brings these advances to a compact, deployment-friendly dense model: a native vision-language model that understands images and videos, with flexible thinking control, designed to carry complex, multi-step tasks through to completion with greater reliability. For streamlined integration, we recommend using Qwen3.8 via APIs. Qwen3.8 can be…

Open weights apache-2.0 27.8B parameters 262,144 tokens transformers

[View model](https://savrn.com/models/qwen3-8-27b-2)

Model

### [Qwen3.8-27B](https://savrn.com/models/qwen3-8-27b-3)

[Comfy Org](https://savrn.com/model-publishers/comfy-org)

Repackaged model files for ComfyUI. Currently only used for text generation. - https://huggingface.co/Qwen/Qwen3.8-27B Place the files in the following folders

Open weights apache-2.0 diffusion-single-file

[View model](https://savrn.com/models/qwen3-8-27b-3)

Model · Image and text to text

### [Qwen3.8-27B](https://savrn.com/models/qwen3-8-27b-4)

[Vocabor Silentii](https://savrn.com/model-publishers/vocaborsilentii)

Following the widespread community adoption of the Qwen3.5 and Qwen3.6 series, we are pleased to introduce Qwen3.8, the most capable generation in the Qwen open-model family to date. Built on the architectural foundation of Qwen3.5, Qwen3.8 delivers substantial gains across coding, professional work, research, and long-horizon agentic tasks. Qwen3.8-27B brings these advances to a compact, deployment-friendly dense model: a native vision-language model that understands images and videos, with flexible thinking control, designed to carry complex, multi-step tasks through to completion with greater reliability. For streamlined integration, we recommend using Qwen3.8 via APIs. Qwen3.8 can be…

Open weights apache-2.0 27.8B parameters 262,144 tokens transformers

[View model](https://savrn.com/models/qwen3-8-27b-4)

Model · Image and text to text

### [Qwen3.8-27B](https://savrn.com/models/qwen3-8-27b-5)

[Ares Realm Studios](https://savrn.com/model-publishers/ares-realm-studios)

Following the widespread community adoption of the Qwen3.5 and Qwen3.6 series, we are pleased to introduce Qwen3.8, the most capable generation in the Qwen open-model family to date. Built on the architectural foundation of Qwen3.5, Qwen3.8 delivers substantial gains across coding, professional work, research, and long-horizon agentic tasks. Qwen3.8-27B brings these advances to a compact, deployment-friendly dense model: a native vision-language model that understands images and videos, with flexible thinking control, designed to carry complex, multi-step tasks through to completion with greater reliability. For streamlined integration, we recommend using Qwen3.8 via APIs. Qwen3.8 can be…

Open weights apache-2.0 27.8B parameters 262,144 tokens transformers

[View model](https://savrn.com/models/qwen3-8-27b-5)

Model · Image and text to text

### [Qwen3.8-27B](https://savrn.com/models/qwen3-8-27b-6)

[Yinzhipeng123](https://savrn.com/model-publishers/yinzhipeng123)

Following the widespread community adoption of the Qwen3.5 and Qwen3.6 series, we are pleased to introduce Qwen3.8, the most capable generation in the Qwen open-model family to date. Built on the architectural foundation of Qwen3.5, Qwen3.8 delivers substantial gains across coding, professional work, research, and long-horizon agentic tasks. Qwen3.8-27B brings these advances to a compact, deployment-friendly dense model: a native vision-language model that understands images and videos, with flexible thinking control, designed to carry complex, multi-step tasks through to completion with greater reliability. For streamlined integration, we recommend using Qwen3.8 via APIs. Qwen3.8 can be…

Open weights apache-2.0 27.8B parameters 262,144 tokens transformers

[View model](https://savrn.com/models/qwen3-8-27b-6)

Model · Text generation

### [Qwen3.8-27B-24GB-128k-GGUF](https://savrn.com/models/qwen3-8-27b-24gb-128k-gguf)

[Jordan Dominick](https://savrn.com/model-publishers/jdominick05)

Three GGUF quantizations of Qwen/Qwen3.8-27B that spend bits where quantization error hurts most: the 16 full-attention layers and the recurrent (linear-attention) layers get more precision, the bulky feed-forward up/gate weights get less. Built for running the model at a 128k context entirely on one 24 GB GPU (measured on an RX 7900 XTX with llama.cpp/ROCm). All are text-only (no vision projector). Unsloth's mmproj-F16.gguf from unsloth/Qwen3.8-27B-GGUF is built from the same base model and should work with them, but this was not tested. R1 and R2 keep the multi-token-prediction (MTP) layer, quantized with the same recipe; R3 drops it (64 blocks, nextnpredictlayers = 0), so it cannot be…

Open weights apache-2.0 gguf

[View model](https://savrn.com/models/qwen3-8-27b-24gb-128k-gguf)

Model · Image and text to text

### [Qwen3.8-27B-6bit-MLX](https://savrn.com/models/qwen3-8-27b-6bit-mlx)

[Timothy Chia](https://savrn.com/model-publishers/timothyckl)

A 6-bit affine MLX quantization of Qwen/Qwen3.8-27B, using a group size of 64. See the base model card for model details, intended uses, and limitations.

Open weights apache-2.0 27.4B parameters 262,144 tokens mlx

[View model](https://savrn.com/models/qwen3-8-27b-6bit-mlx)

Model

### [Qwen3.8-27B-AutoRound-NVFP4](https://savrn.com/models/qwen3-8-27b-autoround-nvfp4)

[Jl](https://savrn.com/model-publishers/jia0160)

Open weights 16.7B parameters 262,144 tokens

[View model](https://savrn.com/models/qwen3-8-27b-autoround-nvfp4)

Model · Any to any

### [Qwen3.8-27B-BF16-SSMFIX-apostate-GSQ-RCO-IQ3_S](https://savrn.com/models/qwen3-8-27b-bf16-ssmfix-apostate-gsq-rco-iq3-s)

[Sky](https://savrn.com/model-publishers/redashes)

Qwen3.8-27B (bf16 source, ssmfix chat template applied) quantized with a per-tensor mixed scheme derived from GSQ grid learning + RCO Riemannian tangent-projection search. Search domain {2,3,4} bit, target avg ~3.5 bpw; result: IQ3S-dominant mix (IQ3S=144, IQ4XS=96, IQ3XXS=78 tensors), avg bpw 3.52, 866 tensors, 12.0 GB. Built with llama-quantize + imatrix (fineweb-edu style corpus) from the bf16 -> f16 GGUF (converthftogguf.py). Includes MTP head; pair with mmproj-Qwen3.8-27B-Q5K-MIX for vision. Measured on RTX 3080 20G (llama-kvmem-server, kv q80, draft-mtp n=3): decode ~48.5 t/s, prefill ~1150 t/s.

Open weights apache-2.0

[View model](https://savrn.com/models/qwen3-8-27b-bf16-ssmfix-apostate-gsq-rco-iq3-s)

Model

### [Qwen3.8-27B-BF16-hygon-FlagOS](https://savrn.com/models/qwen3-8-27b-bf16-hygon-flagos)

[FlagRelease](https://savrn.com/model-publishers/flagrelease)

Alibaba open‑sources the vision‑language model Qwen3.8‑27B, and the Zhongzhi (众智) FlagOS community simultaneously completes Day 0 multi‑chip adaptation; based on the FlagOS unified open‑source technology stack, Qwen3.8‑27B has finished multi‑chip adaptation, precision alignment and deployment verification across 11 AI chips including T-Head（平头哥）、NVIDIA（英伟达）、Moore Threads（摩尔线程）、MetaX（沐曦）、Kunlunxin（昆仑芯）、Ascend（华为昇腾）、Hygon（海光）、Iluvatar CoreX（天数智芯）、Tsingmicro（清微智能）、Enflame（燧原科技）and Sunrise（曦望）, among which NVIDIA and Moore Threads support FP8 precision deployment while the rest run on BF16, and FlagOS has for the first time extended the adaptation of the latest Qwen model to ARM edge‑side…

Open weights apache-2.0 262,144 tokens

[View model](https://savrn.com/models/qwen3-8-27b-bf16-hygon-flagos)

Model

### [Qwen3.8-27B-BF16-zhenwu-FlagOS](https://savrn.com/models/qwen3-8-27b-bf16-zhenwu-flagos)

[FlagRelease](https://savrn.com/model-publishers/flagrelease)

Alibaba open‑sources the vision‑language model Qwen3.8‑27B, and the Zhongzhi (众智) FlagOS community simultaneously completes Day 0 multi‑chip adaptation; based on the FlagOS unified open‑source technology stack, Qwen3.8‑27B has finished multi‑chip adaptation, precision alignment and deployment verification across 11 AI chips including T-Head（平头哥）、NVIDIA（英伟达）、Moore Threads（摩尔线程）、MetaX（沐曦）、Kunlunxin（昆仑芯）、Ascend（华为昇腾）、Hygon（海光）、Iluvatar CoreX（天数智芯）、Tsingmicro（清微智能）、Enflame（燧原科技）and Sunrise（曦望）, among which NVIDIA and Moore Threads support FP8 precision deployment while the rest run on BF16, and FlagOS has for the first time extended the adaptation of the latest Qwen model to ARM edge‑side…

Open weights apache-2.0 262,144 tokens

[View model](https://savrn.com/models/qwen3-8-27b-bf16-zhenwu-flagos)

Model · Image and text to text

### [Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-NVFP4-NInfer](https://savrn.com/models/qwen3-8-27b-coder390-efficientthink-opus5-5-gpt6astra-grok4-7-dsv4pro-k3-sft-rloo-nvfp4-ni)

[Lynn](https://savrn.com/model-publishers/nerkyor)

A model post-trained with several rounds of SFT and RLOO on top of Qwen3.8-27B-EfficientThink-SFT-SimPO-DFlash2, which is itself the official Qwen3.8-27B post-trained with SFT and SimPO. It is built to fix the original model's habit of failing to stop: it already has an answer, yet keeps re-deriving until it hits the 94K cap with no final answer. This repository provides the three NVFP4 tiers, NVFP4 W4A16 (NVFP4/W4A16/), NVFP4 W4A4 (NVFP4/W4A4/), and NVFP4 W4A4-W8A8 (NVFP4/W4A4-W8A8/, mixed precision)—all fully multimodal (text + image/video) with the official BF16 MTP bundled and their own DFlash2 draft (DFlash2-FP8/) inside each tier directory, loading in SGLang without patches—plus two…

Open weights apache-2.0

[View model](https://savrn.com/models/qwen3-8-27b-coder390-efficientthink-opus5-5-gpt6astra-grok4-7-dsv4pro-k3-sft-rloo-nvfp4-ni)

Model

### [Qwen3.8-27B-Coder390-GGUF](https://savrn.com/models/qwen3-8-27b-coder390-gguf)

[Huang Liang](https://savrn.com/model-publishers/hl1973)

Open weights

[View model](https://savrn.com/models/qwen3-8-27b-coder390-gguf)

## Model Collections

Hand-picked starting points, each with the reason it exists.

Collection · 4 entries

### [Embedding models for retrieval](https://savrn.com/collections/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.

[View collection](https://savrn.com/collections/embedding-models-for-retrieval)

Collection · 4 entries

### [Models that fit on one accelerator](https://savrn.com/collections/models-that-run-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.

[View collection](https://savrn.com/collections/models-that-run-on-one-accelerator)

Collection · 6 entries

### [Open-weight text models worth knowing](https://savrn.com/collections/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.

[View collection](https://savrn.com/collections/open-weight-text-models-worth-knowing)

Collection · 3 entries

### [Speech and audio models](https://savrn.com/collections/speech-and-audio)

Recognition and synthesis models, grouped so the two directions are easy to compare.

[View collection](https://savrn.com/collections/speech-and-audio)

## 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](https://savrn.com/ai-index/pricing/open-models)

The same open-weight model priced by every host that serves it, per million tokens.

Research Hub

### [Data center trackers and maps](https://savrn.com/data-center-research)

Moratoriums, permits, power, water and capital behind the facilities that run these models.

Method

### [How the Model Hub is built](https://savrn.com/model-hub/methodology)

Sources, evidence labels, refresh behaviour, and the limits of every comparison here.