community pool / model answer
GLM-5.2-REAP50-Q3_K_M-GGUF
chat · pipenetwork/GLM-5.2-REAP50-Q3_K_M-GGUF
22.1 tok/s · model median · 1 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| RTX 3090 24GB ×10 | 3-bit | 22.1 tok/s | reported | 92 | - GB | 262,144 | 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.