community pool / model answer
Ling-3.0-tiny
chat · inclusionAI/Ling-3.0-tiny
128.8 tok/s · model median · 4 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| AMD BC-250 | 8-bit | 88.8 tok/s | reported | 2,021 | - GB | 2,048 | llama.cpp |
| RTX 3060 12GB | 4-bit | 104.8 tok/s | reported | 137,729 | 7.7 GB | 262,144 | llama.cpp |
| RTX PRO 6000 Blackwell 96GB | 4-bit | 369.1 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.