qwen35 27B
92 records across 5 hardware.
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| GeForce RTX 3090 | qwen35 27B | Q5_K - Medium | llama.cpp (CUDA) | 77.24 | 1715.55 | – | – | tg512 | 2026-09-07 | community | – | source |
| GeForce RTX 3090 | qwen35 27B | Q5_K - Medium | llama.cpp (CUDA) | 75.34 | 2045.61 | – | – | tg512 | 2026-09-07 | community | – | source |
| GeForce RTX 3090 | qwen35 27B | Q5_K - Medium | llama.cpp (CUDA) | 75.18 | 2045.01 | – | – | tg512 | 2026-09-07 | community | – | source |
| GeForce RTX 3090 | qwen35 27B | Q5_K - Medium | llama.cpp (CUDA) | 74.75 | 2047.57 | – | – | tg512 | 2026-09-07 | community | – | source |
| GeForce RTX 3090 | qwen35 27B | Q5_K - Medium | llama.cpp (CUDA) | 74.61 | 2050.92 | – | – | tg512 | 2026-09-07 | community | – | source |
| GeForce RTX 3090 | qwen35 27B | Q5_K - Medium | llama.cpp (CUDA) | 74.48 | 2051.13 | – | – | tg512 | 2026-09-07 | community | – | source |
| GeForce RTX 3090 | qwen35 27B | Q5_K - Medium | llama.cpp (CUDA) | 39.0 | 1403.46 | – | – | tg512 | 2026-09-07 | community | – | source |
| GeForce RTX 3090 | qwen35 27B | Q5_K - Medium | llama.cpp (CUDA) | 38.99 | 1401.5 | – | – | tg512 | 2026-09-07 | community | – | source |
| GeForce RTX 3090 | qwen35 27B | Q5_K - Medium | llama.cpp (CUDA) | 38.99 | 1401.56 | – | – | tg512 | 2026-09-07 | community | – | source |
| GeForce RTX 3090 | qwen35 27B | Q5_K - Medium | llama.cpp (CUDA) | 38.98 | 1397.03 | – | – | tg512 | 2026-09-07 | community | – | source |
| GeForce RTX 3090 | qwen35 27B | Q5_K - Medium | llama.cpp (CUDA) | 38.98 | 1404.01 | – | – | tg512 | 2026-09-07 | community | – | source |
| GeForce RTX 3090 | qwen35 27B | Q5_K - Medium | llama.cpp (CUDA) | 38.98 | 1403.68 | – | – | tg512 | 2026-09-07 | community | – | source |
| GeForce RTX 3090 | qwen35 27B | Q5_K - Medium | llama.cpp (CUDA) | 38.57 | 1379.75 | – | – | tg512 | 2026-09-07 | community | contradiction | source |
| GeForce RTX 3090 | qwen35 27B | Q5_K - Medium | llama.cpp (CUDA) | 38.57 | 1377.26 | – | – | tg512 | 2026-09-07 | community | – | source |
| GeForce RTX 3090 | qwen35 27B | Q5_K - Medium | llama.cpp (CUDA) | 38.56 | 1382.0 | – | – | tg512 | 2026-09-07 | community | – | source |
| GeForce RTX 3090 | qwen35 27B | Q5_K - Medium | llama.cpp (CUDA) | 38.54 | 1380.63 | – | – | tg512 | 2026-09-07 | community | – | source |
| GeForce RTX 3090 | qwen35 27B | Q5_K - Medium | llama.cpp (CUDA) | 38.54 | 1379.84 | – | – | tg512 | 2026-09-07 | community | – | source |
| GeForce RTX 3090 | qwen35 27B | Q5_K - Medium | llama.cpp (CUDA) | 38.54 | 1382.78 | – | – | tg512 | 2026-09-07 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q4_0 | llama.cpp (SYCL) | 27.59 | 815.63 | – | – | tg128 | 2026-08-27 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q4_0 | llama.cpp (SYCL) | 27.53 | 792.89 | – | – | tg128 | 2026-09-01 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q4_0 | llama.cpp (SYCL) | 27.48 | 813.56 | – | – | tg128 | 2026-09-01 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q4_0 | llama.cpp (SYCL) | 27.4 | 358.96 | – | – | tg128 | 2026-08-27 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q4_0 | llama.cpp (SYCL) | 27.37 | 355.72 | – | – | tg128 | 2026-09-01 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q4_0 | llama.cpp (SYCL) | 27.36 | 353.01 | – | – | tg128 | 2026-09-01 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q4_0 | llama.cpp (SYCL) | 27.07 | 239.5 | – | – | tg128 | 2026-09-01 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q4_0 | llama.cpp (SYCL) | 27.05 | 270.79 | – | – | tg128 | 2026-09-01 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q4_0 | llama.cpp (SYCL) | 26.89 | 812.57 | – | – | tg128 | 2026-08-27 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q4_0 | llama.cpp (SYCL) | 26.77 | 354.67 | – | – | tg128 | 2026-08-27 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q4_K - Medium | llama.cpp (SYCL) | 24.97 | 867.21 | – | – | tg128 | 2026-08-27 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q4_K - Medium | llama.cpp (SYCL) | 24.86 | 756.78 | – | – | tg128 | 2026-08-27 | community | – | source |
| M5 Max | qwen35 27B | 6bit | oMLX | 24.7 | 785.8 | – | – | 1024 | 2026-10-09 | community | – | source |
| M5 Max | qwen35 27B | 6bit | oMLX | 24.6 | 882.4 | – | – | 4096 | 2026-10-09 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q5_K - Medium | llama.cpp (SYCL) | 23.22 | 1024.19 | – | – | tg128 | 2026-08-29 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q5_K - Medium | llama.cpp (SYCL) | 23.17 | 914.54 | – | – | tg128 | 2026-08-29 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q4_K - Medium | llama.cpp (SYCL) | 22.92 | 875.38 | – | – | tg128 | 2026-08-29 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q5_K - Medium | llama.cpp (SYCL) | 22.88 | 935.68 | – | – | tg128 | 2026-07-10 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q4_K - Medium | llama.cpp (SYCL) | 22.86 | 853.39 | – | – | tg128 | 2026-08-29 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q5_K - Medium | llama.cpp (SYCL) | 22.81 | 837.0 | – | – | tg128 | 2026-07-10 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q5_K - Small | llama.cpp (SYCL) | 22.4 | 914.77 | – | – | tg128 | 2026-09-01 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q5_K - Small | llama.cpp (SYCL) | 22.33 | 845.78 | – | – | tg128 | 2026-09-01 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q5_K - Medium | llama.cpp (SYCL) | 22.31 | 978.1 | – | – | tg128 | 2026-08-27 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q5_K - Medium | llama.cpp (SYCL) | 22.31 | 948.86 | – | – | tg128 | 2026-09-01 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q5_K - Medium | llama.cpp (SYCL) | 22.3 | 970.49 | – | – | tg128 | 2026-09-01 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q5_K - Medium | llama.cpp (SYCL) | 22.26 | 311.0 | – | – | tg128 | 2026-09-01 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q5_K - Medium | llama.cpp (SYCL) | 22.25 | 815.38 | – | – | tg128 | 2026-09-01 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q5_K - Medium | llama.cpp (SYCL) | 22.24 | 1031.14 | – | – | tg128 | 2026-08-27 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q5_K - Medium | llama.cpp (SYCL) | 22.24 | 843.67 | – | – | tg128 | 2026-08-27 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q5_K - Medium | llama.cpp (SYCL) | 22.22 | 840.86 | – | – | tg128 | 2026-09-01 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q5_K - Medium | llama.cpp (SYCL) | 22.22 | 858.88 | – | – | tg128 | 2026-09-01 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q5_K - Medium | llama.cpp (SYCL) | 22.17 | 791.62 | – | – | tg128 | 2026-09-01 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q5_K - Medium | llama.cpp (SYCL) | 22.17 | 304.89 | – | – | tg128 | 2026-09-01 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q5_K - Medium | llama.cpp (SYCL) | 22.11 | 833.6 | – | – | tg128 | 2026-08-27 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q5_K - Medium | llama.cpp (SYCL) | 21.41 | 949.64 | – | – | tg512 | 2026-08-21 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q4_K - Medium | llama.cpp (SYCL) | 21.39 | 811.78 | – | – | tg128 | 2026-09-01 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q4_K - Medium | llama.cpp (SYCL) | 21.33 | 784.04 | – | – | tg128 | 2026-09-01 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q6_K | llama.cpp (SYCL) | 21.25 | 979.33 | – | – | tg128 | 2026-09-01 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q6_K | llama.cpp (SYCL) | 21.21 | 973.08 | – | – | tg128 | 2026-08-27 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q6_K | llama.cpp (SYCL) | 21.15 | 789.89 | – | – | tg128 | 2026-08-27 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q6_K | llama.cpp (SYCL) | 21.15 | 793.28 | – | – | tg128 | 2026-09-01 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q4_K - Medium | llama.cpp (SYCL) | 20.53 | 788.86 | – | – | tg512 | 2026-08-21 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q6_K | llama.cpp (SYCL) | 20.08 | 984.56 | – | – | tg128 | 2026-08-27 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q6_K | llama.cpp (SYCL) | 19.93 | 715.19 | – | – | tg128 | 2026-08-27 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q6_K | llama.cpp (SYCL) | 19.75 | 950.58 | – | – | tg512 | 2026-08-21 | community | – | source |
| M5 Max | qwen35 27B | 8bit | oMLX | 19.1 | 784.7 | – | – | 1024 | 2026-10-09 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q6_K | llama.cpp (SYCL) | 18.91 | 1035.09 | – | – | tg128 | 2026-08-29 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q6_K | llama.cpp (SYCL) | 18.86 | 688.23 | – | – | tg128 | 2026-08-29 | community | – | source |
| M5 Max | qwen35 27B | 8bit | oMLX | 18.8 | 937.0 | – | – | 4096 | 2026-10-09 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q8_0 | llama.cpp (Vulkan) | 18.6 | 1138.09 | – | – | tg128 | 2026-08-26 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q8_0 | llama.cpp (Vulkan) | 18.56 | 1140.11 | – | – | tg128 | 2026-08-26 | community | – | source |
| Arc A770 | qwen35 27B | Q4_K - Medium | llama.cpp (SYCL) | 17.63 | 524.5 | – | – | tg128 | 2026-08-17 | community | – | source |
| Arc A770 | qwen35 27B | Q4_K - Medium | llama.cpp (SYCL) | 17.4 | 452.7 | – | – | tg128 | 2026-08-17 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q8_0 | llama.cpp (SYCL) | 16.66 | 1046.98 | – | – | tg128 | 2026-08-26 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q8_0 | llama.cpp (SYCL) | 16.64 | 335.62 | – | – | tg128 | 2026-08-26 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q8_0 | llama.cpp (SYCL) | 16.63 | 572.1 | – | – | tg128 | 2026-08-26 | community | – | source |
| Arc Pro B70 | qwen35 27B | Q8_0 | llama.cpp (SYCL) | 16.6 | 300.36 | – | – | tg128 | 2026-08-26 | community | – | source |
| Arc Pro B70 | qwen35 27B | IQ4_XS - 4.25 bpw | llama.cpp (SYCL) | 16.51 | 274.41 | – | – | tg128 | 2026-09-01 | community | – | source |
| Arc Pro B70 | qwen35 27B | IQ4_XS - 4.25 bpw | llama.cpp (SYCL) | 16.43 | 571.95 | – | – | tg128 | 2026-09-01 | community | – | source |
| Arc Pro B70 | qwen35 27B | IQ4_XS - 4.25 bpw | llama.cpp (SYCL) | 16.42 | 273.2 | – | – | tg128 | 2026-09-01 | community | – | source |
| Arc Pro B70 | qwen35 27B | IQ4_XS - 4.25 bpw | llama.cpp (SYCL) | 16.4 | 583.02 | – | – | tg128 | 2026-09-01 | community | – | source |
| Arc Pro B70 | qwen35 27B | IQ4_XS - 4.25 bpw | llama.cpp (SYCL) | 16.4 | 560.78 | – | – | tg128 | 2026-09-01 | community | – | source |
| Arc Pro B70 | qwen35 27B | IQ4_XS - 4.25 bpw | llama.cpp (SYCL) | 16.34 | 586.82 | – | – | tg128 | 2026-09-01 | community | – | source |
| Arc Pro B60 | qwen35 27B | Q4_K - Medium | llama.cpp | 14.92 | 508.73 | – | – | tg128 | 2026-08-29 | community | – | source |
| Arc Pro B60 | qwen35 27B | Q4_K - Medium | llama.cpp | 14.92 | 507.51 | – | – | tg128 | 2026-08-29 | community | – | source |
| Arc Pro B60 | qwen35 27B | Q4_K - Medium | llama.cpp | 14.92 | 185.63 | – | – | tg128 | 2026-08-29 | community | – | source |
| Arc Pro B60 | qwen35 27B | Q4_K - Medium | llama.cpp | 14.92 | 186.28 | – | – | tg128 | 2026-08-29 | community | – | source |
| Arc Pro B60 | qwen35 27B | Q4_K - Small | llama.cpp | 13.26 | 459.73 | – | – | tg128 | 2026-08-29 | community | – | source |
| Arc Pro B60 | qwen35 27B | Q4_K - Small | llama.cpp | 13.25 | 456.99 | – | – | tg128 | 2026-08-29 | community | – | source |
| Arc Pro B60 | qwen35 27B | Q4_K - Small | llama.cpp | 13.25 | 179.83 | – | – | tg128 | 2026-08-29 | community | – | source |
| Arc Pro B60 | qwen35 27B | Q4_K - Small | llama.cpp | 13.25 | 180.7 | – | – | tg128 | 2026-08-29 | community | – | source |
| Arc Pro B70 | qwen35 27B | IQ3_XXS - 3.0625 bpw | llama.cpp (SYCL) | 10.28 | 445.32 | – | – | tg128 | 2026-08-27 | community | – | source |
| Arc Pro B70 | qwen35 27B | IQ3_XXS - 3.0625 bpw | llama.cpp (SYCL) | 10.23 | 436.31 | – | – | tg128 | 2026-08-27 | community | – | source |
| Arc A770 | qwen35 27B | Q4_K - Medium | llama.cpp (SYCL) | 8.61 | 516.6 | – | – | tg128 | 2026-08-17 | community | – | source |