Qwen 3.8 2.4T A95B
Qwen 3.8 2.4T A95B is a large language model developed by Qwen, released as an open-source chat model. It is designed for complex, multi-step agentic tasks and shows top-tier performance in coding and specialized benchmarks.
Input
Output
Context
1010K
Max Output
131K
Parameters
2446.2B
Technical Specifications
Model TypeChat
Context Window1,010,000 tokens
Max Output Tokens131,072 tokens
Parameters2446.2B
Release DateAug 8, 2026
Training CutoffNot available
Licenseother
Open SourceYes
Input Modalities
Text
Output Modalities
Text
Capabilities
Benchmarks
Artificial Analysis
42.4%
HLE
75.3%
AA-LCR
93.5%
GPQA
51.6%
SciCode
49.1%
Tau2 Banking
71.9
Coding
57.7
Intelligence
82.0%
Terminal-Bench 2.1
23.8
Speed (tok/s)
85.9
TTFA (s)
1.7
TTFT (s)
Resources & Links
More Models by Qwen
qwen3-235b-a22b-thinking-2507262K context · 235B · Open weightsQwen 3 4B Thinking 2507262K context · 4B · Open weightsQwen 2.5 32B Instruct33K context · 32.8B · Open weightsQwen 2.5 14B Instruct AWQ33K context · 14.8B · Open weightsQwen 3 VL 8B Instruct262K context · 8.8B · Open weightsQwen 3 VL Reranker 2B262K context · 2.1B · Open weights
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Aug 28, 2026
Your AI stack shouldn't stand still.
Every month new models become cheaper, faster, and more capable. Inferbase ensures your application automatically benefits without changing a single API call.