GLM-5.3
68 records across 8 hardware.
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| TP4 | GLM-5.3 | BF16 | vLLM | 870.4 | – | – | – | tg1000 | 2026-09-26 | community | – | source |
| TP4 | GLM-5.3 | BF16 | vLLM | 826.2 | – | – | – | tg1000 | 2026-09-26 | community | – | source |
| 4x H200 NVL | GLM-5.3 | NVFP4 | vllm | 823.9 | – | – | – | – | 2026-09-30 | community | – | source |
| 4x H200 NVL | GLM-5.3 | NVFP4 | vllm | 761.1 | – | – | – | – | 2026-09-30 | community | – | source |
| 64 H100 | GLM-5.3 | unstated | vLLM | 602 | – | – | 21.6 | – | 2026-10 | sourced | – | source |
| 64 H100 | GLM-5.3 | unstated | vLLM | 563 | – | – | 87.5 | – | 2026-10 | sourced | – | source |
| 64 H100 | GLM-5.3 | unstated | vLLM | 547 | – | – | 98.2 | – | 2026-10 | sourced | – | source |
| 64 H100 | GLM-5.3 | unstated | vLLM | 520 | – | – | 183 | – | 2026-10 | sourced | – | source |
| 64 H100 | GLM-5.3 | unstated | vLLM | 503 | – | – | 89.0 | – | 2026-10 | sourced | – | source |
| 64 H100 | GLM-5.3 | unstated | vLLM | 482 | – | – | 194 | – | 2026-10 | sourced | – | source |
| TP4 | GLM-5.3 | BF16 | vLLM | 412.4 | – | – | – | tg1000 | 2026-09-26 | community | – | source |
| TP4 | GLM-5.3 | BF16 | vLLM | 398.5 | – | – | – | tg1000 | 2026-09-26 | community | – | source |
| 4x H200 NVL | GLM-5.3 | NVFP4 | vllm | 329.8 | – | – | – | – | 2026-09-30 | community | – | source |
| 4x H200 NVL | GLM-5.3 | NVFP4 | vllm | 279.2 | – | – | – | – | 2026-09-30 | community | – | source |
| TP4 | GLM-5.3 | BF16 | vLLM | 176.8 | – | – | – | tg1000 | 2026-09-26 | community | – | source |
| TP4 | GLM-5.3 | BF16 | vLLM | 175.4 | – | – | – | tg1000 | 2026-09-26 | community | – | source |
| 4x H200 NVL | GLM-5.3 | NVFP4 | vllm | 119.1 | – | – | – | – | 2026-09-30 | community | – | source |
| 4x H200 NVL | GLM-5.3 | NVFP4 | vllm | 110.7 | – | – | – | – | 2026-09-30 | community | – | source |
| 8x MI355X | GLM-5.3 | MXFP4 | vLLM | 106.11 | – | – | – | 8192 | 2026-10-06 | sourced | – | source |
| 8x MI355X | GLM-5.3 | MXFP4 | vLLM | 105.16 | – | – | – | 8192 | 2026-10-06 | sourced | – | source |
| B300 | GLM-5.3 | MXFP4 | vLLM | 91.6 | – | – | – | 1024 | 2026-10-22 | sourced | – | source |
| B300 | GLM-5.3 | MXFP4 | vLLM | 86.66 | – | – | – | 1024 | 2026-10-22 | sourced | – | source |
| 8x MI355X | GLM-5.3 | MXFP4 | vLLM | 85.72 | – | – | – | 8192 | 2026-10-06 | sourced | – | source |
| 8x MI355X | GLM-5.3 | MXFP4 | vLLM | 62.31 | – | – | – | 8192 | 2026-10-06 | sourced | – | source |
| 8x MI355X | GLM-5.3 | MXFP4 | vLLM | 61.02 | – | – | – | 8192 | 2026-10-06 | sourced | – | source |
| M5 Ultra | GLM-5.3 | oQ4e | oMLX | 50.5 | 1837.0 | – | – | 199680 | 2026-10-11 | community | – | source |
| M5 Ultra | GLM-5.3 | oQ4e | oMLX | 50.4 | 1830.0 | – | – | 199680 | 2026-10-08 | community | – | source |
| 8x MI355X | GLM-5.3 | MXFP4 | vLLM | 36.67 | – | – | – | 8192 | 2026-10-06 | sourced | – | source |
| 8x MI355X | GLM-5.3 | MXFP4 | vLLM | 27.34 | – | – | – | 60000 | 2026-10-06 | sourced | – | source |
| 8x MI355X | GLM-5.3 | MXFP4 | vLLM | 27.22 | – | – | – | 60000 | 2026-10-06 | sourced | – | source |
| 8x MI355X | GLM-5.3 | MXFP4 | vLLM | 24.88 | – | – | – | 60000 | 2026-10-06 | sourced | – | source |
| 8x MI355X | GLM-5.3 | MXFP4 | vLLM | 23.13 | – | – | – | 60000 | 2026-10-06 | sourced | – | source |
| M3 Ultra | GLM-5.3 | mixed 3_6bit | oMLX | 21.2 | 214.2 | – | – | 1024 | 2026-10-10 | community | – | source |
| M3 Ultra | GLM-5.3 | mixed 3_6bit | oMLX | 21.2 | 214.2 | – | – | 1024 | 2026-10-10 | community | – | source |
| 8x MI355X | GLM-5.3 | MXFP4 | vLLM | 19.62 | – | – | – | 60000 | 2026-10-06 | sourced | – | source |
| M3 Ultra | GLM-5.3 | 4bit | oMLX | 19.1 | 219.8 | – | – | 1024 | 2026-10-17 | community | – | source |
| M3 Ultra | GLM-5.3 | 4bit | oMLX | 18.0 | 226.5 | – | – | 4096 | 2026-10-17 | community | – | source |
| M3 Ultra | GLM-5.3 | 4bit | oMLX | 17.8 | 202.6 | – | – | 8192 | 2026-10-17 | community | – | source |
| M3 Ultra | GLM-5.3 | 4bit | oMLX | 17.6 | 187.5 | – | – | 16384 | 2026-10-17 | community | – | source |
| M3 Ultra | GLM-5.3 | 4bit | oMLX | 17.2 | 181.1 | – | – | 32768 | 2026-10-17 | community | – | source |
| M3 Ultra | GLM-5.3 | 4bit | oMLX | 16.7 | 174.7 | – | – | 65536 | 2026-10-17 | community | – | source |
| 8x MI355X | GLM-5.3 | MXFP4 | vLLM | 16.62 | – | – | – | 60000 | 2026-10-06 | sourced | – | source |
| M3 Ultra | GLM-5.3 | mixed 4_5bit | oMLX | 15.9 | 160.4 | – | – | 16384 | 2026-10-10 | community | – | source |
| M3 Ultra | GLM-5.3 | mixed 3_6bit | oMLX | 15.7 | 219.4 | – | – | 4096 | 2026-10-10 | community | – | source |
| M3 Ultra | GLM-5.3 | mixed 3_6bit | oMLX | 15.7 | 197.1 | – | – | 8192 | 2026-10-10 | community | – | source |
| M3 Ultra | GLM-5.3 | mixed 3_6bit | oMLX | 15.7 | 219.4 | – | – | 4096 | 2026-10-10 | community | – | source |
| M3 Ultra | GLM-5.3 | mixed 3_6bit | oMLX | 15.7 | 197.1 | – | – | 8192 | 2026-10-10 | community | – | source |
| M3 Ultra | GLM-5.3 | 4bit | oMLX | 15.0 | 166.1 | – | – | 131072 | 2026-10-17 | community | – | source |
| M3 Ultra | GLM-5.3 | mixed 4/8bit | oMLX | 14.7 | 197.5 | – | – | 1024 | 2026-10-07 | community | – | source |
| M3 Ultra | GLM-5.3 | 4bit | oMLX | 14.4 | 158.7 | – | – | 199680 | 2026-10-17 | community | – | source |
| M3 Ultra | GLM-5.3 | 4bit | oMLX | 13.5 | 184.1 | – | – | 4096 | 2026-10-17 | community | contradiction | source |
| M3 Ultra | GLM-5.3 | 4bit | oMLX | 12.9 | 120.0 | – | – | 16384 | 2026-10-16 | community | contradiction | source |
| M3 Ultra | GLM-5.3 | mixed 4_5bit | oMLX | 12.4 | 154.6 | – | – | 199680 | 2026-10-10 | community | – | source |
| 4x H200 NVL | GLM-5.3 | NVFP4 | vllm | – | 5092 | – | – | 32768 | 2026-09-30 | community | – | source |
| 4x H200 NVL | GLM-5.3 | NVFP4 | vllm | – | 5129 | – | – | 32768 | 2026-09-30 | community | – | source |
| 4x H200 NVL | GLM-5.3 | NVFP4 | vllm | – | 4941 | – | – | 131072 | 2026-09-30 | community | – | source |
| 4x H200 NVL | GLM-5.3 | NVFP4 | vllm | – | 4988 | – | – | 131072 | 2026-09-30 | community | – | source |
| 4x H200 NVL | GLM-5.3 | NVFP4 | vllm | – | 5103 | – | – | 32768 | 2026-09-30 | community | – | source |
| 4x B300 | GLM-5.3 | NVFP4 | vLLM | – | 51.5 | – | – | – | 2026-10 | community | – | source |
| 4x B300 | GLM-5.3 | NVFP4 | vLLM | – | 142.7 | – | – | – | 2026-10 | community | – | source |
| 4x B300 | GLM-5.3 | NVFP4 | vLLM | – | 144.1 | – | – | – | 2026-10 | community | – | source |
| 4x B300 | GLM-5.3 | NVFP4 | vLLM | – | 146.0 | – | – | – | 2026-10 | community | – | source |
| 4x B300 | GLM-5.3 | NVFP4 | vLLM | – | 62.2 | – | – | – | 2026-10 | community | – | source |
| 4x B300 | GLM-5.3 | NVFP4 | vLLM | – | 39.7 | – | – | – | 2026-10 | community | – | source |
| 4x B300 | GLM-5.3 | NVFP4 | vLLM | – | 62.2 | – | – | – | 2026-10 | community | – | source |
| 4x B300 | GLM-5.3 | NVFP4 | vLLM | – | 59.0 | – | – | – | 2026-10 | community | – | source |
| 4x B300 | GLM-5.3 | NVFP4 | vLLM | – | 102.1 | – | – | – | 2026-10 | community | – | source |
| 4x B300 | GLM-5.3 | NVFP4 | vLLM | – | 102.0 | – | – | – | 2026-10 | community | – | source |