Skip to content
Weights Not Walls
Menu

Qwen

Qwen3.8-Flash-Next

Reviewedaccepts images
Size
180B parameterscounted from the safetensors header on the Hub
Licence
custom, read it, Qwen Community License 1.0Our reading, check the licence: A custom licence we have not read for this model: other makers use the same name for different texts. Read the model's own licence file before you use it.Licence text
On the Hub since
24 Aug 2026the date the repo was created
Context length
256k tokensfrom the model's config
Kind
Base model (no base model declared on the Hub)Qwen4ExpForConditionalGeneration
On Hugging Face
Qwen/Qwen3.8-Flash-Next2.9M downloads in the last 30 days, 7.3k likes

Scores

No independent scores for this model in Epoch AI's data. A score is only shown here when Epoch's name for a model matches this repo with certainty; an uncertain match is left out rather than guessed.

Claimed by the maker Claimed

The model card has no claimed scores in a machine-readable form (the card's model-index), so none are shown. The maker may give scores in the card text: read the card.

Other views, which we link to and do not copy: look this model up on Artificial Analysis and the Arena leaderboard.

Run it yourself

file sizes read from the Hub 19 Nov 2026

Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 0.19 GB, worked out from the model's config (Qwen/Qwen3.8-Flash-Next), at 16-bit precision. Choose a machine above to see a verdict for each format. Method

GGUF for llama.cpp, Ollama, LM Studio and others

ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF (converted by ISTA-DASLab), 7.3M downloads. Sizes are the real files on the Hub, all parts added up. For image input you also need the projector file mmproj-Qwen3.8-Flash-Next-BF16.gguf (0.85 GB), not counted below.

FormatSizeMemory neededGet it
Q2_061.9 GBfile size, 2 parts62.5 GB61.9 + 0.19 + 0.50
Commands
llama.cpp
llama-server -hf ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF:Q2_0
Download
hf download ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF --include "Q2_0/Qwen3.8-Flash-Next-GSQ-RCO-Q2_0-*-of-00002.gguf" --local-dir Qwen3.8-Flash-Next-GSQ-RCO-GGUF
IQ2_XS63.4 GBfile size, 2 parts64.0 GB63.4 + 0.19 + 0.50
Commands
llama.cpp
llama-server -hf ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF:IQ2_XS
Download
hf download ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF --include "IQ2_XS/Qwen3.8-Flash-Next-GSQ-RCO-IQ2_XS-*-of-00002.gguf" --local-dir Qwen3.8-Flash-Next-GSQ-RCO-GGUF
IQ3_XXS70.6 GBfile size, 2 parts71.3 GB70.6 + 0.19 + 0.50
Commands
llama.cpp
llama-server -hf ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF:IQ3_XXS
Download
hf download ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF --include "IQ3_XXS/Qwen3.8-Flash-Next-GSQ-RCO-IQ3_XXS-*-of-00002.gguf" --local-dir Qwen3.8-Flash-Next-GSQ-RCO-GGUF
IQ3_S77.9 GBfile size, 2 parts78.6 GB77.9 + 0.19 + 0.50
Commands
llama.cpp
llama-server -hf ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF:IQ3_S
Download
hf download ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF --include "IQ3_S/Qwen3.8-Flash-Next-GSQ-RCO-IQ3_S-*-of-00002.gguf" --local-dir Qwen3.8-Flash-Next-GSQ-RCO-GGUF

MLX for Apple silicon

FormatSizeMemory neededRepo
MLX 4bitsh0wie/Qwen3.8-Flash-Next-REAP-288-MLX-4bit68.4 GBfile size69.1 GB68.4 + 0.19 + 0.50Download page
MLXYoussofal/Qwen3.8-Flash-Next-MTPLX-Optimized-Speed107.1 GBfile size107.8 GB107.1 + 0.19 + 0.50Download page

Original weights size from the safetensors header, for vLLM, SGLang, Transformers

FormatSizeMemory neededRepo
BF16original weights335.3 GBfile size336.0 GB335.3 + 0.19 + 0.50
hf download Qwen/Qwen3.8-Flash-Next --local-dir Qwen3.8-Flash-Next
Other conversions (14; sizes not read)

The Hub tags 100 or more quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.

Run it by API

Hugging Face Inference Providers, fetched 19 Nov 2026, 13:58 UTC

1 provider serves this model through the Hugging Face router. Prices are US dollars per million tokens. Precision is what the provider reports; a lower precision than the original weights can change answers. Live first, then cheapest output.

ProviderInOutContextPrecisionTokens/sFirst tokenUptime 24hToolsJSON
nscaleserves Qwen/Qwen3.8-Flash-Next-FP8$0.15$0.471Mnot given1730.4 s?yesyes

Through the router, with a Hugging Face token (the router bills your Hugging Face account). Change the name after the colon to pick another provider.

curl https://router.huggingface.co/v1/chat/completions \ -H "Authorization: Bearer $HF_TOKEN" -H "Content-Type: application/json" \ -d '{"model": "Qwen/Qwen3.8-Flash-Next-FP8:nscale", "messages": [{"role": "user", "content": "Hello"}]}'

Not built yet: one key for every open model, with BlockRun, and our own tested-quality score per provider. Until then, precision and measured speed are the best guide to a provider here.

Fine-tunes of this model

from our snapshot of the Hub

Repos that declare this model as their base, most downloaded first. Listing is not a recommendation; unreviewed ones have not been checked.

Planned for this page Not built yet

Try it in private chat
A link to Solana AI's confidential chat for the models it serves. This model is not listed as served there.
Fine-tune it
Fine-tuning a few base models from this page and publishing the result here.
Creators and earnings
Pages for people who publish fine-tunes and adapters of this model, and what they earn.
Fund and bounties
Bounties for new open models, paid from a public fund. How the fund will work.
Contribute compute
How to give compute to open model work, with Akash.

Model data from the Hugging Face Hub 19 Nov 2026, 13:43 UTC. The repo. Found a mistake on this page? Tell us.