Qwen3.6-35B-A3B-FP8
Qwen/Qwen3.6-35B-A3B-FP8
A popular open vision-language model, with 6.2M downloads a month. gigarouter benchmarks and hosts it as an OpenAI-compatible API.
about this model
Qwen3.6-35B-A3B-FP8 is a causal language model with a vision encoder (VLM) hosted on gigarouter as an OpenAI-compatible API. It contains 35 billion total parameters with 3 billion activated through a mixture-of-experts architecture (256 experts, 8 routed plus 1 shared expert). Fine-grained FP8 quantization (block size 128) yields performance nearly identical to the original model. Native context length is 262,144 tokens, extensible to approximately 1,010,000 tokens.
Key Capabilities
Optimised for agentic coding, particularly frontend workflows and repository-level reasoning. A new thinking preservation feature retains reasoning context from historical messages, reducing overhead in iterative development. The model also handles general agent tasks.
Benchmark Results
Coding agent benchmarks (compared to Qwen3.5-27B, Gemma4-31B, Qwen3.5-35BA3B, and Gemma4-26BA4B):
| Qwen3.5-27B | Gemma4-31B | Qwen3.5-35BA3B | Gemma4-26BA4B | Qwen3.6-35BA3B | |
|---|---|---|---|---|---|
| Coding Agent | |||||
| SWE-bench Verified | 75.0 | 52.0 | 70.0 | 17.4 | 73.4 |
| SWE-bench Multilingual | 69.3 | 51.7 | 60.3 | 17.3 | 67.2 |
| SWE-bench Pro | 51.2 | 35.7 | 44.6 | 13.8 | 49.5 |
| Terminal-Bench 2.0 | 41.6 | 42.9 | 40.5 | 34.2 | 51.5 |
| Claw-Eval (Avg) | 64.3 | 48.5 | 65.4 | 58.8 | 68.7 |
| Claw-Eval (Pass^3) | 46.2 | 25.0 | 51.0 | 28.0 | 50.0 |
| SkillsBench (Avg5) | 27.2 | 23.6 | 4.4 | 12.3 | 28.7 |
| QwenClawBench | 52.2 | 41.7 | 47.7 | 38.7 | 52.6 |
| NL2Repo | 27.3 | 15.5 | 20.5 | 11.6 | 29.4 |
| QwenWebBench | 1068 | 1197 | 978 | 1178 | 1397 |
| General Agent | |||||
| TAU3-Bench | 68.4 | 67.5 | 68.9 | 59.0 | 67.2 |
For further details, refer to the Qwen3.6-35B-A3B blog post.
We're benchmarking and onboarding Qwen3.6-35B-A3B-FP8 as a hosted, OpenAI-compatible API. Sign in for free credit and be ready when it lands, or tell us you want it and we'll prioritize it.