community pool / model answer
Qwen3.6-35B-A3B-NVFP4
chat · RedHatAI/Qwen3.6-35B-A3B-NVFP4
102.1 tok/s · model median · 5 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| GB10 Grace Blackwell 128GB | 4-bit | 94.8 tok/s | measured | 153 | 87 GB | 262,144 | vllm |
| RTX 5090 32GB | 4-bit | 183.3 tok/s | reported | 122 | 31.3 GB | 262,144 | vllm |
| RTX 5090 32GB ×2 | 4-bit | 340.8 tok/s | reported | 1,111 | 58.9 GB | 32,768 | vllm |
Context tested
The table above is the tested context for each exact rig and quantization cell. Empty fields remain empty rather than being filled with an estimate.