community pool / model answer
SmolLM2-360M-Instruct
chat · HuggingFaceTB/SmolLM2-360M-Instruct
189.9 tok/s · model median · 4 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| AMD Ryzen 7 7840HS | 2-bit | 208 tok/s | reported | - | - GB | 2,048 | llama.cpp |
| AMD Ryzen 7 7840HS | 4-bit | 171.8 tok/s | reported | - | - GB | 2,048 | llama.cpp |
| AMD Ryzen 7 7840HS | 8-bit | 130.6 tok/s | reported | - | - GB | 2,048 | llama.cpp |
| RTX 3060 12GB | 8-bit | 437 tok/s | reported | 229 | 1.9 GB | 4,608 | 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.