Skip to content

Qwen3.8 2.4T A95B

Qwen/Qwen3.8-2.4T-A95B
Open Source · chat · open-weights
Open Alert me on changes
Context
1M
Max output
Weights
Open
API $/1M
$2.00 / $6.00
Modalities
text
Released
08 Aug 2026
License: other · Qwen/Qwen3.8-2.4T-A95B
Download image Share on X Share on LinkedIn
AI summary
● machine-written

Qwen3.8 2.4T A95B: 2.4T sparse MoE open-weight model

Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model with 95 billion active parameters out of 2.4 trillion total parameters. It is the open-weight variant of Qwen3.8 Max, designed for coding, research, complex reasoning, and agentic workflows. The model is available through multiple providers via OpenRouter's API.

What's new
  • Open-weight sparse mixture-of-experts architecture with 95B active / 2.4T total parameters
  • Open-weight variant of Qwen3.8 Max
  • 1M token context window
  • Multi-provider hosting with OpenRouter routing options
Best for
CodingResearchComplex reasoningAgentic workflows
Sources

Source: https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B