community pool / model answer
gemma-3-1b-it-GGUF
chat · ggml-org/gemma-3-1b-it-GGUF
281.9 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 | 325.2 tok/s | reported | - | 1.5 GB | 4,096 | llama.cpp |
| RTX A5000 24GB | 8-bit | 281.9 tok/s | reported | - | 1.8 GB | 4,096 | llama.cpp |
| TECNO POVA 7 Ultra 5G / Mali-G615 MC6 11.23GB | 4-bit | 19.1 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.