Source: Artificial Analysis / Qwen3.5 397B A17B (Non-reasoning)LMSpeed rank: #92 / 113Updated: Jul 9, 2026Confidence: 4
8853.3 tok/s
8952.0 tok/s
9051.1 tok/s
9150.0 tok/s
92Qwen3.5 397B A17B48.9 tok/s
93
The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher infere...
Scores across benchmark categories on a 0-100 scale.
Input and output token limits for this model, plus how it ranks on long-context understanding.
2 metrics
2 metrics
2 metrics
1 metric
Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.Artificial AnalysisStandard benchmark data may include BenchLM and other public sources.