community pool / model answer
Tinystories-gpt-0.1-3m
chat · segestic/Tinystories-gpt-0.1-3m
4,911.9 tok/s · model median · 5 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| AMD Ryzen 7 7840HS | 2-bit | 4,979.4 tok/s | reported | - | - GB | 2,048 | llama.cpp |
| AMD Ryzen 7 7840HS | 4-bit | 4,980.7 tok/s | reported | - | - GB | 2,048 | llama.cpp |
| AMD Ryzen 7 7840HS | 8-bit | 4,911.9 tok/s | reported | - | - GB | 2,048 | llama.cpp |
| AMD Ryzen 7 7840HS | 16-bit | 4,747.6 tok/s | reported | - | - GB | 2,048 | llama.cpp |
| RTX 3060 12GB | 8-bit | 1,298.2 tok/s | reported | 53 | 1.3 GB | 1,024 | 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.