community pool / model answer
Qwen2.5-1.5B-Instruct-GGUF
chat · Qwen/Qwen2.5-1.5B-Instruct-GGUF
268 tok/s · model median · 5 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| RTX A5000 24GB | 4-bit | 320.6 tok/s | reported | - | 1.6 GB | 4,096 | llama.cpp |
| RTX A5000 24GB | 8-bit | 268 tok/s | reported | - | 2.2 GB | 4,096 | llama.cpp |
| TECNO POVA 7 Ultra 5G / Mali-G615 MC6 11.23GB | 4-bit | 18.6 tok/s | reported | - | - GB | 640 | 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.