Qwen 3.5 397B A17B FP8
Qwen develops the Qwen 3.5 397B A 17B model, a chat model that excels at tasks such as code generation, reasoning, and text generation, with a notable strength in multimodal understanding thanks to its unified vision-language foundation. Its efficient hybrid architecture, combining Gated Delta Networks and sparse Mixture-of-Experts, enables high-throughput inference with minimal latency.
Input
Output
Context
262K
Max Output
66K
Parameters
397B
Technical Specifications
Model TypeChat
Context Window262,144 tokens
Max Output Tokens66,000 tokens
Parameters397B
Release DateFeb 18, 2026
Training CutoffNov 1, 2025
Licenseapache-2.0
Open SourceYes
Input Modalities
TextImage
Output Modalities
Text
Capabilities
Benchmarks
Artificial Analysis
27.3%
HLE
89.3%
GPQA
42.0%
SciCode
41.3
Coding
33.7
Intelligence
50.5
Speed (tok/s)
64.8
TTFA (s)
1.7
TTFT (s)
Resources & Links
Estimated GPU Requirements for Qwen 3.5 397B A17B FP8
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 24, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.