community pool / model answer
GLM-4.7-Flash
chat · zai-org/GLM-4.7-Flash
97.4 tok/s · model median · 4 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| Radeon AI Pro R9700 32GB ×2 | 4-bit | 92.9 tok/s | reported | 110 | - GB | 783 | llama.cpp |
| Radeon AI Pro R9700 32GB ×3 | 4-bit | 97.4 tok/s | reported | 253 | 21.6 GB | 783 | llama.cpp |
| RTX 5090 32GB | 6-bit | 175.9 tok/s | reported | 13 | 25 GB | 8,192 | llama.cpp |
| RX 7700 XT 12GB | 4-bit | 21.5 tok/s | reported | 102 | - GB | 2,048 | 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.