Qwen 3.8 27B FP8
Qwen 3.8 27B FP8 is a 27-billion parameter chat model developed by Qwen. It is a native vision-language model capable of processing text and image inputs, and it excels in coding and agentic task execution.
Input
Output
Context
1000K
Max Output
66K
Parameters
27.8B
Technical Specifications
Model TypeChat
Context Window1,000,000 tokens
Max Output Tokens65,536 tokens
Parameters27.8B
Release DateAug 13, 2026
Training CutoffNot available
Licenseapache-2.0
Open SourceYes
Input Modalities
TextImage
Output Modalities
Text
Capabilities
Benchmarks
Artificial Analysis
33.9%
HLE
77.3%
AA-LCR
90.5%
GPQA
44.7%
SciCode
48.0%
Tau2 Banking
68.1
Coding
52.0
Intelligence
79.8%
Terminal-Bench 2.1
46.9
Speed (tok/s)
43.9
TTFA (s)
1.3
TTFT (s)
Resources & Links
Estimated GPU Requirements for Qwen 3.8 27B FP8
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
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.