Qwen3.5-35B-A3B
173 records across 23 hardware.
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| RTX PRO 6000 Blackwell Max-Q | Qwen3.5-35B-A3B 35B MoE A3B | BF16 | vLLM | 3341.89 | – | – | – | – | 2026-02 | community | – | source |
| DGX Spark | Qwen3.5-35B-A3B 35B MoE A3B | BF16 | vLLM | 431.42 | – | – | – | – | 2026-02 | community | – | source |
| H100 | Qwen3.5-35B-A3B 35B MoE (A3B active) | FP8 | vLLM | 195 | – | – | – | – | 2026-04 | community | – | source |
| M5 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 154.2 | 4666.0 | – | – | 1024 | 2026-10-12 | community | – | source |
| M5 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 154.2 | 4666.0 | – | – | 1024 | 2026-10-12 | community | – | source |
| M5 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 149.7 | 4624.0 | – | – | 1024 | 2026-10-10 | community | – | source |
| M5 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 142.5 | 2675.0 | – | – | 4096 | 2026-10-16 | community | – | source |
| M5 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 136.3 | 4323.0 | – | – | 1024 | 2026-10-12 | community | contradiction | source |
| M5 Max (48 GB) | Qwen3.5-35B-A3B | 4bit | MLX | 128 | 3235 | – | – | 8000 | – | sourced | – | source |
| M5 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 124.9 | 4914.0 | – | – | 32768 | 2026-10-12 | community | – | source |
| M5 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 124.9 | 4914.0 | – | – | 32768 | 2026-10-12 | community | – | source |
| M5 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 113.0 | 4597.0 | – | – | 4096 | 2026-10-07 | community | contradiction | source |
| M5 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 103.5 | 3674.0 | – | – | 65536 | 2026-10-12 | community | – | source |
| M5 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 103.5 | 3674.0 | – | – | 65536 | 2026-10-12 | community | – | source |
| M5 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 99.3 | 738.4 | – | – | 1024 | 2026-10-16 | community | contradiction | source |
| M5 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 98.6 | 2566.0 | – | – | 1024 | 2026-10-07 | community | – | source |
| M3 Ultra | Qwen3.5-35B-A3B | oQ4e | oMLX | 98.4 | 2441.0 | – | – | 8192 | 2026-10-10 | community | – | source |
| M5 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 97.5 | 4123.0 | – | – | 16384 | 2026-10-07 | community | – | source |
| M5 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 96.6 | 3276.0 | – | – | 4096 | 2026-10-07 | community | – | source |
| M4 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 95.8 | 1067.0 | – | – | 4096 | 2026-03-09 | community | – | source |
| M4 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 95.8 | 1067.0 | – | – | 4096 | 2026-03-09 | community | – | source |
| M4 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 95.8 | 1067.0 | – | – | 4096 | 2026-03-09 | community | – | source |
| M4 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 95.7 | 1361.0 | – | – | 1024 | 2026-03-09 | community | – | source |
| M4 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 95.7 | 1361.0 | – | – | 1024 | 2026-03-09 | community | – | source |
| M4 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 95.7 | 1361.0 | – | – | 1024 | 2026-03-09 | community | – | source |
| M3 Ultra (256 GB) | Qwen3.5-35B-A3B | 4bit | MLX | 95 | – | – | – | – | – | sourced | – | source |
| M4 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 93.4 | 1652.0 | – | – | 1024 | 2026-03-09 | community | – | source |
| M4 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 93.4 | 1652.0 | – | – | 1024 | 2026-03-09 | community | – | source |
| M4 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 93.4 | 1652.0 | – | – | 1024 | 2026-03-09 | community | – | source |
| M4 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 93.4 | 1652.0 | – | – | 1024 | 2026-03-09 | community | – | source |
| M4 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 93.4 | 1652.0 | – | – | 1024 | 2026-03-09 | community | – | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 92.7 | 880.9 | – | – | 1024 | 2026-10-08 | community | – | source |
| M4 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 90.5 | 1091.0 | – | – | 8192 | 2026-03-09 | community | – | source |
| M4 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 90.5 | 1091.0 | – | – | 8192 | 2026-03-09 | community | – | source |
| M4 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 90.5 | 1091.0 | – | – | 8192 | 2026-03-09 | community | – | source |
| M4 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 90.0 | 1487.0 | – | – | 8192 | 2026-03-09 | community | – | source |
| M4 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 90.0 | 1487.0 | – | – | 8192 | 2026-03-09 | community | – | source |
| M4 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 90.0 | 1487.0 | – | – | 8192 | 2026-03-09 | community | – | source |
| M4 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 90.0 | 1487.0 | – | – | 8192 | 2026-03-09 | community | – | source |
| M4 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 90.0 | 1487.0 | – | – | 8192 | 2026-03-09 | community | – | source |
| M5 Max (48 GB) | Qwen3.5-35B-A3B | Q4_K - Medium | llama.cpp | 89.4 | 783 | – | – | 8000 | – | sourced | – | source |
| M4 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 88.6 | 1706.0 | – | – | 4096 | 2026-03-09 | community | – | source |
| M4 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 88.6 | 1706.0 | – | – | 4096 | 2026-03-09 | community | – | source |
| M4 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 88.6 | 1706.0 | – | – | 4096 | 2026-03-09 | community | – | source |
| M4 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 88.6 | 1706.0 | – | – | 4096 | 2026-03-09 | community | – | source |
| M4 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 88.6 | 1706.0 | – | – | 4096 | 2026-03-09 | community | – | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 87.7 | 1059.0 | – | – | 4096 | 2026-10-08 | community | – | source |
| M5 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 85.7 | 2776.0 | – | – | 16384 | 2026-10-16 | community | – | source |
| M5 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 84.3 | 1384.0 | – | – | 4096 | 2026-10-16 | community | contradiction | source |
| M3 Ultra | Qwen3.5-35B-A3B | oQ4e | oMLX | 84.0 | 1883.0 | – | – | 32768 | 2026-10-10 | community | – | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 82.8 | 867.2 | – | – | 1024 | 2026-03-09 | community | contradiction | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 82.8 | 867.2 | – | – | 1024 | 2026-03-09 | community | contradiction | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 82.8 | 867.2 | – | – | 1024 | 2026-03-09 | community | contradiction | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 82.8 | 867.2 | – | – | 1024 | 2026-03-09 | community | contradiction | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 82.8 | 867.2 | – | – | 1024 | 2026-03-09 | community | contradiction | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 82.8 | 867.2 | – | – | 1024 | 2026-03-09 | community | contradiction | source |
| M3 Ultra (256 GB) | Qwen3.5-35B-A3B | 8bit | MLX | 80 | – | – | – | – | – | sourced | – | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 79.2 | 899.9 | – | – | 4096 | 2026-03-09 | community | – | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 79.2 | 899.9 | – | – | 4096 | 2026-03-09 | community | – | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 79.2 | 899.9 | – | – | 4096 | 2026-03-09 | community | – | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 79.2 | 899.9 | – | – | 4096 | 2026-03-09 | community | – | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 79.2 | 899.9 | – | – | 4096 | 2026-03-09 | community | – | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 79.2 | 899.9 | – | – | 4096 | 2026-03-09 | community | – | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 79.1 | 879.6 | – | – | 4096 | 2026-03-09 | community | – | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 79.1 | 879.6 | – | – | 4096 | 2026-03-09 | community | – | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 79.1 | 879.6 | – | – | 4096 | 2026-03-09 | community | – | source |
| M5 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 76.4 | 2414.0 | – | – | 131072 | 2026-10-12 | community | – | source |
| M5 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 76.4 | 2414.0 | – | – | 131072 | 2026-10-12 | community | – | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 75.6 | 821.5 | – | – | 1024 | 2026-03-09 | community | contradiction | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 75.6 | 821.5 | – | – | 1024 | 2026-03-09 | community | contradiction | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 75.6 | 821.5 | – | – | 1024 | 2026-03-09 | community | contradiction | source |
| M5 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 75.1 | 2219.0 | – | – | 4096 | 2026-10-15 | community | – | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 74.9 | 876.2 | – | – | 8192 | 2026-03-09 | community | – | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 74.9 | 876.2 | – | – | 8192 | 2026-03-09 | community | – | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 74.9 | 876.2 | – | – | 8192 | 2026-03-09 | community | – | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 74.9 | 876.2 | – | – | 8192 | 2026-03-09 | community | – | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 74.9 | 876.2 | – | – | 8192 | 2026-03-09 | community | – | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 74.9 | 876.2 | – | – | 8192 | 2026-03-09 | community | – | source |
| M4 | Qwen3.5-35B-A3B | 2bit | oMLX | 72.3 | 467.8 | – | – | 1024 | 2026-10-12 | community | – | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 71.9 | 873.4 | – | – | 8192 | 2026-03-09 | community | – | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 71.9 | 873.4 | – | – | 8192 | 2026-03-09 | community | – | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 71.9 | 873.4 | – | – | 8192 | 2026-03-09 | community | – | source |
| M6 | Qwen3.5-35B-A3B | 4bit | oMLX | 68.4 | 2132.0 | – | – | 4096 | 2026-10-11 | community | – | source |
| M6 | Qwen3.5-35B-A3B | 4bit | oMLX | 68.4 | 2132.0 | – | – | 4096 | 2026-10-11 | community | – | source |
| M4 | Qwen3.5-35B-A3B | 2bit | oMLX | 68.4 | 515.5 | – | – | 4096 | 2026-10-12 | community | – | source |
| M5 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 67.3 | 1475.0 | – | – | 1024 | 2026-10-08 | community | contradiction | source |
| M5 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 67.2 | 1608.0 | – | – | 4096 | 2026-10-08 | community | contradiction | source |
| M5 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 65.9 | 2129.0 | – | – | 16384 | 2026-10-15 | community | – | source |
| M1 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 63.7 | 540.2 | – | – | 1024 | 2026-03-09 | community | – | source |
| M1 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 63.7 | 540.2 | – | – | 1024 | 2026-03-09 | community | – | source |
| M4 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 63.7 | 1227.0 | – | – | 16384 | 2026-03-09 | community | – | source |
| M4 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 63.7 | 1227.0 | – | – | 16384 | 2026-03-09 | community | – | source |
| M4 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 63.7 | 1227.0 | – | – | 16384 | 2026-03-09 | community | – | source |
| M4 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 63.7 | 1227.0 | – | – | 16384 | 2026-03-09 | community | – | source |
| M4 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 63.7 | 1227.0 | – | – | 16384 | 2026-03-09 | community | – | source |
| M5 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 63.5 | 1827.0 | – | – | 199680 | 2026-10-12 | community | – | source |
| M5 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 63.5 | 1827.0 | – | – | 199680 | 2026-10-12 | community | – | source |
| M6 | Qwen3.5-35B-A3B | 4bit | oMLX | 61.5 | 1920.0 | – | – | 16384 | 2026-10-11 | community | – | source |
| M6 | Qwen3.5-35B-A3B | 4bit | oMLX | 61.5 | 1920.0 | – | – | 16384 | 2026-10-11 | community | – | source |
| M1 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 60.1 | 585.0 | – | – | 4096 | 2026-03-09 | community | – | source |
| M1 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 60.1 | 585.0 | – | – | 4096 | 2026-03-09 | community | – | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 57.7 | 805.6 | – | – | 16384 | 2026-03-09 | community | – | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 57.7 | 805.6 | – | – | 16384 | 2026-03-09 | community | – | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 57.7 | 805.6 | – | – | 16384 | 2026-03-09 | community | – | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 57.7 | 805.6 | – | – | 16384 | 2026-03-09 | community | – | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 57.7 | 805.6 | – | – | 16384 | 2026-03-09 | community | – | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 57.7 | 805.6 | – | – | 16384 | 2026-03-09 | community | – | source |
| M1 Max (64 GB) | Qwen3.5-35B-A3B | 4bit | MLX | 57.6 | 431 | – | – | 8000 | – | sourced | – | source |
| M1 Max (64 GB) | Qwen3.5-35B-A3B | 4bit | LM Studio (MLX) | 57 | – | – | – | – | – | sourced | – | source |
| M1 Max | Qwen3.5-35B-A3B | 6bit | oMLX | 56.9 | 571.2 | – | – | 1024 | 2026-10-17 | community | – | source |
| M1 Max | Qwen3.5-35B-A3B | 6bit | oMLX | 55.4 | 656.5 | – | – | 4096 | 2026-10-17 | community | – | source |
| M1 Max | Qwen3.5-35B-A3B | 6bit | oMLX | 50.4 | 524.7 | – | – | 1024 | 2026-03-09 | community | contradiction | source |
| M1 Max | Qwen3.5-35B-A3B | 6bit | oMLX | 50.4 | 524.7 | – | – | 1024 | 2026-03-09 | community | contradiction | source |
| M1 Max | Qwen3.5-35B-A3B | 6bit | oMLX | 49.0 | 558.7 | – | – | 4096 | 2026-03-09 | community | contradiction | source |
| M1 Max | Qwen3.5-35B-A3B | 6bit | oMLX | 49.0 | 558.7 | – | – | 4096 | 2026-03-09 | community | contradiction | source |
| M3 Max | Qwen3.5-35B-A3B | bf16 | oMLX | 48.7 | 1839.0 | – | – | 4096 | 2026-10-12 | community | – | source |
| M1 Max | Qwen3.5-35B-A3B | 8bit | oMLX | 48.3 | 519.9 | – | – | 1024 | 2026-03-09 | community | – | source |
| M1 Max | Qwen3.5-35B-A3B | 8bit | oMLX | 48.3 | 519.9 | – | – | 1024 | 2026-03-09 | community | – | source |
| M1 Max | Qwen3.5-35B-A3B | 8bit | oMLX | 48.0 | 519.6 | – | – | 1024 | 2026-03-09 | community | – | source |
| M1 Max | Qwen3.5-35B-A3B | 8bit | oMLX | 48.0 | 519.6 | – | – | 1024 | 2026-03-09 | community | – | source |
| M5 Max (128 GB) | Qwen3.5-35B-A3B | Q4_K - Medium | Ollama | 48 | – | – | 0.9 | – | – | sourced | – | source |
| M1 Max | Qwen3.5-35B-A3B | 8bit | oMLX | 46.9 | 574.8 | – | – | 4096 | 2026-03-09 | community | – | source |
| M1 Max | Qwen3.5-35B-A3B | 8bit | oMLX | 46.9 | 574.8 | – | – | 4096 | 2026-03-09 | community | – | source |
| M1 Max | Qwen3.5-35B-A3B | 8bit | oMLX | 43.5 | 566.5 | – | – | 4096 | 2026-03-09 | community | – | source |
| M1 Max | Qwen3.5-35B-A3B | 8bit | oMLX | 43.5 | 566.5 | – | – | 4096 | 2026-03-09 | community | – | source |
| M4 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 42.5 | 1026.0 | – | – | 32768 | 2026-03-09 | community | – | source |
| M4 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 42.5 | 1026.0 | – | – | 32768 | 2026-03-09 | community | – | source |
| M4 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 42.5 | 1026.0 | – | – | 32768 | 2026-03-09 | community | – | source |
| M4 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 42.5 | 1026.0 | – | – | 32768 | 2026-03-09 | community | – | source |
| M4 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 42.5 | 1026.0 | – | – | 32768 | 2026-03-09 | community | – | source |
| M5 Pro (64 GB) | Qwen3.5-35B-A3B | Q4_K_L | llama.cpp | 41.9 | – | – | 0.435 | – | – | sourced | – | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 40.6 | 693.2 | – | – | 32768 | 2026-03-09 | community | – | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 40.6 | 693.2 | – | – | 32768 | 2026-03-09 | community | – | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 40.6 | 693.2 | – | – | 32768 | 2026-03-09 | community | – | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 40.6 | 693.2 | – | – | 32768 | 2026-03-09 | community | – | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 40.6 | 693.2 | – | – | 32768 | 2026-03-09 | community | – | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 40.6 | 693.2 | – | – | 32768 | 2026-03-09 | community | – | source |
| M6 | Qwen3.5-35B-A3B | 4bit | oMLX | 38.0 | 1161.0 | – | – | 65536 | 2026-10-11 | community | – | source |
| M1 Max (64 GB) | Qwen3.5-35B-A3B | Q4_K - Medium | LM Studio (llama.cpp) | 29 | – | – | – | – | – | sourced | – | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 25.9 | 537.6 | – | – | 65536 | 2026-03-09 | community | – | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 25.9 | 537.6 | – | – | 65536 | 2026-03-09 | community | – | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 25.9 | 537.6 | – | – | 65536 | 2026-03-09 | community | – | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 25.9 | 537.6 | – | – | 65536 | 2026-03-09 | community | – | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 25.9 | 537.6 | – | – | 65536 | 2026-03-09 | community | – | source |
| M4 Pro | Qwen3.5-35B-A3B | 4bit | oMLX | 25.9 | 537.6 | – | – | 65536 | 2026-03-09 | community | – | source |
| M1 Max | Qwen3.5-35B-A3B | 4bit | oMLX | 18.9 | 411.3 | – | – | 65536 | 2026-03-08 | community | – | source |
| M4 (16 GB) | Qwen3.5-35B-A3B | Q4_K - Medium | llama.cpp | 1.2956 | – | – | 13.0595 | – | – | sourced | – | source |
| 3x RTX PRO 4000 Blackwell | Qwen3.5-35B-A3B | unspecified | CUDA | – | 3078 | – | – | – | 2026-10 | community | – | source |
| 3x RTX PRO 4000 Blackwell | Qwen3.5-35B-A3B | unspecified | CUDA | – | 4393 | – | – | – | 2026-10 | community | – | source |
| 3x RTX PRO 4000 Blackwell | Qwen3.5-35B-A3B | unspecified | CUDA | – | 2814 | – | – | – | 2026-10 | community | – | source |
| 3x RTX PRO 4000 Blackwell | Qwen3.5-35B-A3B | unspecified | CUDA | – | 6274 | – | – | – | 2026-10 | community | – | source |
| RTX 4090 | Qwen3.5-35B-A3B | Q4_K_S | llama.cpp (CUDA) | – | 7473.5 | – | – | – | 2026-10 | community | – | source |
| RTX 4090 | Qwen3.5-35B-A3B | Q4_K_S | llama.cpp (CUDA) | – | 7570.8 | – | – | – | 2026-10 | community | – | source |
| RTX 4090 | Qwen3.5-35B-A3B | Q4_K_S | llama.cpp (CUDA) | – | 7283.5 | – | – | – | 2026-10 | community | – | source |
| RTX 4090 | Qwen3.5-35B-A3B | Q4_K_S | llama.cpp (CUDA) | – | 7370.4 | – | – | – | 2026-10 | community | – | source |
| RTX 4090 | Qwen3.5-35B-A3B | Q4_K_S | llama.cpp (CUDA) | – | 11554.2 | – | – | – | 2026-10 | community | – | source |
| RTX 4090 | Qwen3.5-35B-A3B | Q4_K_S | llama.cpp (CUDA) | – | 11665.8 | – | – | – | 2026-10 | community | – | source |
| RTX PRO 6000 | Qwen3.5-35B-A3B | Q8_0 | llama.cpp | – | 13653.58 | – | – | 2048 | 2026-10-13 | sourced | – | source |
| RTX PRO 6000 | Qwen3.5-35B-A3B | Q8_0 | llama.cpp | – | 16459.56 | – | – | 2048 | 2026-10-13 | sourced | – | source |
| RTX PRO 6000 | Qwen3.5-35B-A3B | Q8_0 | llama.cpp | – | 14090.26 | – | – | 4096 | 2026-10-13 | sourced | – | source |
| RTX PRO 6000 | Qwen3.5-35B-A3B | Q8_0 | llama.cpp | – | 16595.47 | – | – | 4096 | 2026-10-13 | sourced | – | source |
| RTX 5090 | Qwen3.5-35B-A3B | Q4_K_S | llama.cpp | – | 12477.32 | – | – | 2048 | 2026-10-13 | sourced | – | source |
| RTX 5090 | Qwen3.5-35B-A3B | Q4_K_S | llama.cpp | – | 14524.81 | – | – | 2048 | 2026-10-13 | sourced | – | source |
| RTX 5090 | Qwen3.5-35B-A3B | Q4_K_S | llama.cpp | – | 12978.57 | – | – | 4096 | 2026-10-13 | sourced | – | source |
| RTX 5090 | Qwen3.5-35B-A3B | Q4_K_S | llama.cpp | – | 15298.0 | – | – | 4096 | 2026-10-13 | sourced | – | source |
| RTX 4090 | Qwen3.5-35B-A3B | Q4_K_S | llama.cpp | – | 10872.34 | – | – | 2048 | 2026-10-13 | sourced | – | source |
| RTX 4090 | Qwen3.5-35B-A3B | Q4_K_S | llama.cpp | – | 12044.25 | – | – | 2048 | 2026-10-13 | sourced | – | source |
| RTX 4090 | Qwen3.5-35B-A3B | Q4_K_S | llama.cpp | – | 11187.34 | – | – | 4096 | 2026-10-13 | sourced | – | source |
| RTX 4090 | Qwen3.5-35B-A3B | Q4_K_S | llama.cpp | – | 12428.05 | – | – | 4096 | 2026-10-13 | sourced | – | source |
| RTX 3090 | Qwen3.5-35B-A3B | Q4_K_S | llama.cpp | – | 5672.07 | – | – | 2048 | 2026-10-13 | sourced | – | source |
| RTX 3090 | Qwen3.5-35B-A3B | Q4_K_S | llama.cpp | – | 6061.59 | – | – | 2048 | 2026-10-13 | sourced | – | source |
| RTX 3090 | Qwen3.5-35B-A3B | Q4_K_S | llama.cpp | – | 5505.49 | – | – | 4096 | 2026-10-13 | sourced | – | source |
| RTX 3090 | Qwen3.5-35B-A3B | Q4_K_S | llama.cpp | – | 5683.79 | – | – | 4096 | 2026-10-13 | sourced | – | source |