community pool / model answer
GLM-5.2-REAP-504B-GGUF
chat · 0xSero/GLM-5.2-REAP-504B-GGUF
7.9 tok/s · model median · 1 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| GB10 Grace Blackwell 256GB | 2-bit | 7.8 tok/s | reported | 14,878 | 104 GB | 32,768 | llama.cpp |
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.