Qwen3.5-0.8B
171 records across 13 hardware.
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| M5 Max | Qwen3.5-0.8B | 5bit | oMLX | 622.0 | 17226.0 | – | – | 32768 | 2026-10-13 | community | – | source |
| M5 Max | Qwen3.5-0.8B | 5bit | oMLX | 622.0 | 17226.0 | – | – | 32768 | 2026-10-13 | community | – | source |
| M5 Max | Qwen3.5-0.8B | 5bit | oMLX | 389.0 | 19711.0 | – | – | 8192 | 2026-10-13 | community | – | source |
| M5 Max | Qwen3.5-0.8B | 5bit | oMLX | 389.0 | 19711.0 | – | – | 8192 | 2026-10-13 | community | – | source |
| M5 Max | Qwen3.5-0.8B | 5bit | oMLX | 347.3 | 14987.0 | – | – | 1024 | 2026-10-16 | community | – | source |
| M5 Max | Qwen3.5-0.8B | 5bit | oMLX | 331.5 | 17974.0 | – | – | 4096 | 2026-10-13 | community | – | source |
| M5 Max | Qwen3.5-0.8B | 5bit | oMLX | 331.5 | 17974.0 | – | – | 4096 | 2026-10-13 | community | – | source |
| M1 Ultra | Qwen3.5-0.8B | oQ4e | oMLX | 278.9 | 8485.0 | – | – | 8192 | 2026-10-10 | community | – | source |
| M5 Max | Qwen3.5-0.8B | 5bit | oMLX | 275.6 | 12634.0 | – | – | 65536 | 2026-10-13 | community | – | source |
| M5 Max | Qwen3.5-0.8B | 5bit | oMLX | 275.6 | 12634.0 | – | – | 65536 | 2026-10-13 | community | – | source |
| M1 Ultra | Qwen3.5-0.8B | oQ4e | oMLX | 260.9 | 7975.0 | – | – | 8192 | 2026-10-10 | community | – | source |
| M5 Max | Qwen3.5-0.8B | bf16 | oMLX | 247.9 | 17404.0 | – | – | 1024 | 2026-10-12 | community | – | source |
| M5 Max | Qwen3.5-0.8B | bf16 | oMLX | 247.9 | 17404.0 | – | – | 1024 | 2026-10-12 | community | – | source |
| M4 Pro | Qwen3.5-0.8B | oQ8 | oMLX | 242.9 | 4681.0 | – | – | 4096 | 2026-10-15 | community | – | source |
| M5 Max | Qwen3.5-0.8B | bf16 | oMLX | 241.4 | 19054.0 | – | – | 4096 | 2026-10-12 | community | – | source |
| M5 Max | Qwen3.5-0.8B | bf16 | oMLX | 241.4 | 19054.0 | – | – | 4096 | 2026-10-12 | community | – | source |
| M5 Max | Qwen3.5-0.8B | bf16 | oMLX | 240.8 | 15550.0 | – | – | 4096 | 2026-10-12 | community | – | source |
| M5 Max | Qwen3.5-0.8B | oQ8e | oMLX | 237.6 | 8503.0 | – | – | 4096 | 2026-10-10 | community | – | source |
| M5 Max | Qwen3.5-0.8B | bf16 | oMLX | 229.3 | 17192.0 | – | – | 1024 | 2026-10-12 | community | – | source |
| M5 Max | Qwen3.5-0.8B | 5bit | oMLX | 227.0 | 8002.0 | – | – | 131072 | 2026-10-13 | community | – | source |
| M5 Max | Qwen3.5-0.8B | 5bit | oMLX | 227.0 | 8002.0 | – | – | 131072 | 2026-10-13 | community | – | source |
| M4 Pro | Qwen3.5-0.8B | oQ8 | oMLX | 218.7 | 4330.0 | – | – | 1024 | 2026-10-15 | community | – | source |
| M5 | Qwen3.5-0.8B | 4bit | oMLX | 213.5 | 4321.0 | – | – | 1024 | 2026-10-06 | community | – | source |
| M4 Pro | Qwen3.5-0.8B | oQ8 | oMLX | 210.5 | 4988.0 | – | – | 4096 | 2026-10-15 | community | contradiction | source |
| M4 Pro | Qwen3.5-0.8B | oQ8 | oMLX | 207.4 | 4319.0 | – | – | 1024 | 2026-10-15 | community | – | source |
| M4 Pro | Qwen3.5-0.8B | oQ8 | oMLX | 204.5 | 4706.0 | – | – | 8192 | 2026-10-15 | community | – | source |
| M4 Pro | Qwen3.5-0.8B | oQ8 | oMLX | 189.6 | 4332.0 | – | – | 8192 | 2026-10-15 | community | – | source |
| M5 Max | Qwen3.5-0.8B | oQ8e | oMLX | 189.4 | 17371.0 | – | – | 32768 | 2026-10-10 | community | – | source |
| M4 | Qwen3.5-0.8B | 4bit | oMLX | 181.3 | 2114.0 | – | – | 1024 | 2026-10-14 | community | – | source |
| M4 | Qwen3.5-0.8B | 4bit | oMLX | 181.3 | 2114.0 | – | – | 1024 | 2026-10-14 | community | – | source |
| M4 Pro | Qwen3.5-0.8B | oQ8 | oMLX | 181.3 | 4091.0 | – | – | 16384 | 2026-10-15 | community | – | source |
| M5 Max | Qwen3.5-0.8B | bf16 | oMLX | 178.9 | 17501.0 | – | – | 32768 | 2026-10-12 | community | – | source |
| M5 Max | Qwen3.5-0.8B | bf16 | oMLX | 178.9 | 17501.0 | – | – | 32768 | 2026-10-12 | community | – | source |
| M4 Pro | Qwen3.5-0.8B | oQ8 | oMLX | 172.0 | 3716.0 | – | – | 16384 | 2026-10-15 | community | – | source |
| M4 | Qwen3.5-0.8B | 4bit | oMLX | 166.3 | 2161.0 | – | – | 4096 | 2026-10-14 | community | – | source |
| M4 | Qwen3.5-0.8B | 4bit | oMLX | 166.3 | 2161.0 | – | – | 4096 | 2026-10-14 | community | – | source |
| M4 Pro | Qwen3.5-0.8B | oQ8 | oMLX | 165.5 | 2857.0 | – | – | 32768 | 2026-10-15 | community | – | source |
| M5 Max | Qwen3.5-0.8B | 5bit | oMLX | 158.7 | 5736.0 | – | – | 199680 | 2026-10-13 | community | – | source |
| M5 Max | Qwen3.5-0.8B | 5bit | oMLX | 158.7 | 5736.0 | – | – | 199680 | 2026-10-13 | community | – | source |
| M4 Pro | Qwen3.5-0.8B | oQ8 | oMLX | 157.4 | 3198.0 | – | – | 32768 | 2026-10-15 | community | – | source |
| M1 Pro | Qwen3.5-0.8B | OptiQ-4bit | oMLX | 152.9 | 1958.0 | – | – | 4096 | 2026-10-11 | community | – | source |
| M1 Pro | Qwen3.5-0.8B | OptiQ-4bit | oMLX | 152.9 | 1958.0 | – | – | 4096 | 2026-10-11 | community | – | source |
| M5 Max | Qwen3.5-0.8B | oQ8e | oMLX | 148.8 | 12581.0 | – | – | 65536 | 2026-10-10 | community | – | source |
| M5 Max | Qwen3.5-0.8B | 5bit | oMLX | 141.7 | 5203.0 | – | – | 1024 | 2026-10-13 | community | contradiction | source |
| M5 Max | Qwen3.5-0.8B | 5bit | oMLX | 141.7 | 5203.0 | – | – | 1024 | 2026-10-13 | community | contradiction | source |
| M5 Max | Qwen3.5-0.8B | oQ8e | oMLX | 138.5 | 7784.0 | – | – | 131072 | 2026-10-10 | community | – | source |
| M5 Max | Qwen3.5-0.8B | bf16 | oMLX | 138.4 | 13575.0 | – | – | 65536 | 2026-10-12 | community | – | source |
| M5 Max | Qwen3.5-0.8B | bf16 | oMLX | 138.4 | 13575.0 | – | – | 65536 | 2026-10-12 | community | – | source |
| M1 Pro | Qwen3.5-0.8B | 8bit | oMLX | 136.6 | 1929.0 | – | – | 4096 | 2026-10-11 | community | – | source |
| M1 Pro | Qwen3.5-0.8B | 8bit | oMLX | 136.6 | 1929.0 | – | – | 4096 | 2026-10-11 | community | – | source |
| M4 Pro | Qwen3.5-0.8B | oQ8 | oMLX | 135.7 | 1960.0 | – | – | 65536 | 2026-10-15 | community | – | source |
| M1 Pro | Qwen3.5-0.8B | OptiQ-4bit | oMLX | 126.9 | 1406.0 | – | – | 16384 | 2026-10-11 | community | – | source |
| M1 Pro | Qwen3.5-0.8B | OptiQ-4bit | oMLX | 126.9 | 1406.0 | – | – | 16384 | 2026-10-11 | community | – | source |
| M4 Pro | Qwen3.5-0.8B | oQ8 | oMLX | 121.6 | 2214.0 | – | – | 65536 | 2026-10-15 | community | contradiction | source |
| M1 Pro | Qwen3.5-0.8B | 8bit | oMLX | 118.3 | 1416.0 | – | – | 16384 | 2026-10-11 | community | – | source |
| M1 Pro | Qwen3.5-0.8B | 8bit | oMLX | 118.3 | 1416.0 | – | – | 16384 | 2026-10-11 | community | – | source |
| M4 | Qwen3.5-0.8B | 8bit | oMLX | 109.2 | 2200.0 | – | – | 1024 | 2026-03-09 | community | – | source |
| M5 Max | Qwen3.5-0.8B | oQ8e | oMLX | 105.9 | 3444.0 | – | – | 1024 | 2026-10-10 | community | – | source |
| M1 | Qwen3.5-0.8B | 4bit | oMLX | 100.8 | 756.4 | – | – | 1024 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 4bit | oMLX | 100.8 | 756.4 | – | – | 1024 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 4bit | oMLX | 100.8 | 756.4 | – | – | 1024 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 4bit | oMLX | 100.8 | 756.4 | – | – | 1024 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 4bit | oMLX | 100.8 | 756.4 | – | – | 1024 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 4bit | oMLX | 100.8 | 756.4 | – | – | 1024 | 2026-03-09 | community | – | source |
| M4 | Qwen3.5-0.8B | 8bit | oMLX | 99.8 | 2051.0 | – | – | 1024 | 2026-03-09 | community | – | source |
| M4 Pro | Qwen3.5-0.8B | oQ8 | oMLX | 97.1 | 1206.0 | – | – | 131072 | 2026-10-15 | community | – | source |
| M5 Max | Qwen3.5-0.8B | bf16 | oMLX | 92.1 | 9059.0 | – | – | 131072 | 2026-10-12 | community | – | source |
| M5 Max | Qwen3.5-0.8B | bf16 | oMLX | 92.1 | 9059.0 | – | – | 131072 | 2026-10-12 | community | – | source |
| M1 | Qwen3.5-0.8B | 4bit | oMLX | 91.3 | 734.1 | – | – | 4096 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 4bit | oMLX | 91.3 | 734.1 | – | – | 4096 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 4bit | oMLX | 91.3 | 734.1 | – | – | 4096 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 4bit | oMLX | 91.3 | 734.1 | – | – | 4096 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 4bit | oMLX | 91.3 | 734.1 | – | – | 4096 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 4bit | oMLX | 91.3 | 734.1 | – | – | 4096 | 2026-03-09 | community | – | source |
| M5 Max | Qwen3.5-0.8B | oQ8e | oMLX | 90.9 | 5163.0 | – | – | 199680 | 2026-10-10 | community | – | source |
| M4 | Qwen3.5-0.8B | 8bit | oMLX | 90.4 | 1656.0 | – | – | 1024 | 2026-03-09 | community | contradiction | source |
| Intel(R) Core(TM) Ultra 9 285K | Qwen3.5-0.8B | Q4_0 | llama.cpp (CPU) | 86.21 | 889.15 | – | – | tg128 | 2026-10-08 | community | – | source |
| Intel(R) Core(TM) Ultra 9 285K | Qwen3.5-0.8B | Q4_0 | llama.cpp (CPU) | 85.03 | 758.97 | – | – | tg128 | 2026-10-08 | community | – | source |
| M5 Max | Qwen3.5-0.8B | 5bit | oMLX | 84.6 | 5512.0 | – | – | 1024 | 2026-10-16 | community | contradiction | source |
| M2 Ultra | Qwen3.5-0.8B | bf16 | oMLX | 83.2 | 4660.0 | – | – | 65536 | 2026-03-09 | community | – | source |
| M4 Pro | Qwen3.5-0.8B | oQ8 | oMLX | 82.9 | 1396.0 | – | – | 131072 | 2026-10-15 | community | contradiction | source |
| M1 | Qwen3.5-0.8B | 4bit | oMLX | 82.2 | 710.7 | – | – | 8192 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 4bit | oMLX | 82.2 | 710.7 | – | – | 8192 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 4bit | oMLX | 82.2 | 710.7 | – | – | 8192 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 4bit | oMLX | 82.2 | 710.7 | – | – | 8192 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 4bit | oMLX | 82.2 | 710.7 | – | – | 8192 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 4bit | oMLX | 82.2 | 710.7 | – | – | 8192 | 2026-03-09 | community | – | source |
| M4 Pro | Qwen3.5-0.8B | oQ8 | oMLX | 73.3 | 857.9 | – | – | 199680 | 2026-10-15 | community | – | source |
| M5 Ultra | Qwen3.5-0.8B | unknown | oMLX | 71.3 | 10357.0 | – | – | 1024 | 2026-10-18 | community | – | source |
| M5 Max | Qwen3.5-0.8B | bf16 | oMLX | 69.8 | 6308.0 | – | – | 199680 | 2026-10-12 | community | – | source |
| M5 Max | Qwen3.5-0.8B | bf16 | oMLX | 69.8 | 6308.0 | – | – | 199680 | 2026-10-12 | community | – | source |
| M1 | Qwen3.5-0.8B | 4bit | oMLX | 68.2 | 647.6 | – | – | 16384 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 4bit | oMLX | 68.2 | 647.6 | – | – | 16384 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 4bit | oMLX | 68.2 | 647.6 | – | – | 16384 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 4bit | oMLX | 68.2 | 647.6 | – | – | 16384 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 4bit | oMLX | 68.2 | 647.6 | – | – | 16384 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 4bit | oMLX | 68.2 | 647.6 | – | – | 16384 | 2026-03-09 | community | – | source |
| M4 Pro | Qwen3.5-0.8B | oQ8 | oMLX | 62.6 | 938.4 | – | – | 199680 | 2026-10-15 | community | contradiction | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 62.4 | 755.9 | – | – | 1024 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 62.4 | 755.9 | – | – | 1024 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 62.4 | 755.9 | – | – | 1024 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 62.4 | 755.9 | – | – | 1024 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 62.4 | 755.9 | – | – | 1024 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 62.4 | 755.9 | – | – | 1024 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 58.9 | 733.9 | – | – | 4096 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 58.9 | 733.9 | – | – | 4096 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 58.9 | 733.9 | – | – | 4096 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 58.9 | 733.9 | – | – | 4096 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 58.9 | 733.9 | – | – | 4096 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 58.9 | 733.9 | – | – | 4096 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 55.0 | 714.0 | – | – | 8192 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 55.0 | 714.0 | – | – | 8192 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 55.0 | 714.0 | – | – | 8192 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 55.0 | 714.0 | – | – | 8192 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 55.0 | 714.0 | – | – | 8192 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 55.0 | 714.0 | – | – | 8192 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 48.2 | 726.8 | – | – | 1024 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 48.2 | 726.8 | – | – | 1024 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 48.2 | 726.8 | – | – | 1024 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 47.9 | 654.9 | – | – | 16384 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 47.9 | 654.9 | – | – | 16384 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 47.9 | 654.9 | – | – | 16384 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 47.9 | 654.9 | – | – | 16384 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 47.9 | 654.9 | – | – | 16384 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 47.9 | 654.9 | – | – | 16384 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 4bit | oMLX | 47.8 | 552.2 | – | – | 32768 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 4bit | oMLX | 47.8 | 552.2 | – | – | 32768 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 4bit | oMLX | 47.8 | 552.2 | – | – | 32768 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 4bit | oMLX | 47.8 | 552.2 | – | – | 32768 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 4bit | oMLX | 47.8 | 552.2 | – | – | 32768 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 4bit | oMLX | 47.8 | 552.2 | – | – | 32768 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 46.2 | 713.6 | – | – | 1024 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 46.2 | 713.6 | – | – | 1024 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 45.1 | 646.1 | – | – | 8192 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 45.1 | 646.1 | – | – | 8192 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 45.1 | 646.1 | – | – | 8192 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 44.7 | 707.8 | – | – | 4096 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 44.7 | 707.8 | – | – | 4096 | 2026-03-09 | community | – | source |
| M1 Max | Qwen3.5-0.8B | oQ6 | oMLX | 43.4 | 990.5 | – | – | 4096 | 2026-10-13 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 41.2 | 653.5 | – | – | 4096 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 41.2 | 653.5 | – | – | 4096 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 41.2 | 653.5 | – | – | 4096 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 37.3 | 554.7 | – | – | 32768 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 37.3 | 554.7 | – | – | 32768 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 37.3 | 554.7 | – | – | 32768 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 37.3 | 554.7 | – | – | 32768 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 37.3 | 554.7 | – | – | 32768 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 37.3 | 554.7 | – | – | 32768 | 2026-03-09 | community | – | source |
| Dimensity 9400 | Qwen3.5-0.8B 752M | Q4_K_M | llama.cpp (Vulkan) | 36.88 | 54.04 | – | – | tg32 | 2026-10-05 | community | – | source |
| Dimensity 9400 | Qwen3.5-0.8B 752M | Q4_K_M | llama.cpp (Vulkan) | 36.62 | 125.78 | – | – | tg32 | 2026-10-05 | community | – | source |
| Dimensity 9400 | Qwen3.5-0.8B 752M | Q4_K_M | llama.cpp (Vulkan) | 36.4 | 53.3 | – | – | tg32 | 2026-10-05 | community | – | source |
| Dimensity 9400 | Qwen3.5-0.8B 752M | Q4_K_M | llama.cpp (Vulkan) | 36.03 | 54.53 | – | – | tg32 | 2026-10-05 | community | – | source |
| Dimensity 9400 | Qwen3.5-0.8B 752M | Q4_K_M | llama.cpp (Vulkan) | 35.8 | 117.27 | – | – | tg32 | 2026-10-05 | community | – | source |
| M1 Max | Qwen3.5-0.8B | oQ6 | oMLX | 34.6 | 1141.0 | – | – | 16384 | 2026-10-13 | community | – | source |
| M1 Ultra | Qwen3.5-0.8B | oQ4e | oMLX | 31.1 | 5604.0 | – | – | 32768 | 2026-10-10 | community | – | source |
| Phytium D3000M | Qwen3.5-0.8B | Q8_0 | llama.cpp (CPU) | 26.79 | 295.0 | – | – | tg128 | 2026-10-08 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 24.8 | 414.9 | – | – | 65536 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 24.8 | 414.9 | – | – | 65536 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 24.8 | 414.9 | – | – | 65536 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 24.8 | 414.9 | – | – | 65536 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 24.8 | 414.9 | – | – | 65536 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 8bit | oMLX | 24.8 | 414.9 | – | – | 65536 | 2026-03-09 | community | – | source |
| Phytium D3000M | Qwen3.5-0.8B | Q8_0 | llama.cpp (CPU) | 24.4 | 221.4 | – | – | tg128 | 2026-10-08 | community | – | source |
| M1 | Qwen3.5-0.8B | 4bit | oMLX | 17.3 | 408.6 | – | – | 65536 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 4bit | oMLX | 17.3 | 408.6 | – | – | 65536 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 4bit | oMLX | 17.3 | 408.6 | – | – | 65536 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 4bit | oMLX | 17.3 | 408.6 | – | – | 65536 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 4bit | oMLX | 17.3 | 408.6 | – | – | 65536 | 2026-03-09 | community | – | source |
| M1 | Qwen3.5-0.8B | 4bit | oMLX | 17.3 | 408.6 | – | – | 65536 | 2026-03-09 | community | – | source |
| M4 | Qwen3.5-0.8B | unknown | oMLX | 11.7 | 1308.0 | – | – | 1024 | 2026-03-09 | community | – | source |
| Dimensity 9400 | Qwen3.5-0.8B 752M | Q4_K_M | llama.cpp (CPU) | 2.95 | 51.19 | – | – | tg32 | 2026-10-05 | community | – | source |