Open Systems, Blockchain & Business Daily

OSBBD

AI, money and the software behind them.

Qwen3-Coder-Next

Qwen3-Coder-Next is an open-weight language model from Alibaba Qwen, released on February 3, 2026. It is a mixture-of-experts model with 80B total parameters, of which 3B are active for each token. Alibaba Qwen lists a context window of 262,144 tokens. The model takes text input.

Developer
Alibaba Qwen
Released
February 3, 2026
Total parameters
80B
Active parameters per token
3B
Architecture
MoE
Context window
256K
Input
Text
License
Apache 2.0
Commercial use
Yes
Official weights, GB
159.3 GB
Hugging Face repository
huggingface.co
Checked on

The weights are released under Apache 2.0, which allows commercial use.

The official weights on Hugging Face take about 159 GB. Running the model needs at least that much memory across GPUs and system RAM, plus room for the context cache; quantized versions need less.

Total parameters, billions
80B
Active parameters, billions
3B
Context window, tokens
262.14K
License type
Apache 2.0
License conditions
Apache 2.0, with no user or revenue limits.
Official quantized or alternative versions
Qwen/Qwen3-Coder-Next-FP8; Qwen/Qwen3-Coder-Next-GGUF
License text
huggingface.co
Sources
PageURL
Hugging Face model cardhttps://huggingface.co/Qwen/Qwen3-Coder-Next/raw/main/README.md
Hugging Face weights indexhttps://huggingface.co/Qwen/Qwen3-Coder-Next/raw/main/model.safetensors.index.json
GitHub filehttps://raw.githubusercontent.com/QwenLM/Qwen3-Coder/main/README.md
Qwen on LinkedInhttps://www.linkedin.com/posts/qwen_introducingqwen3-coder-next-an-open-weight-activity-7424484355294576640-1Vi0
OSBBD

What are you looking for?

Search by headline, topic or keyword.