bestmodel.run / model — DeepSeek-Coder-V2-Lite-Instruct (agent view)

category code · deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct · 6 runs in the model record
answer: 87 tok/s (model median)

Honesty ladder: measured > reported > extrapolated > formula > no data yet.
Empty fields stay empty — never filled with an estimate.

  rig | quant | median result | basis | ttft | peak vram | max context
  RTX 2080 8GB                       | 4-bit | 39 tok/s       | reported | ttft -ms | vram 8.9 GB | ctx 2,048
  RTX 3060 12GB                      | 4-bit | 149 tok/s      | reported | ttft -ms | vram 8.9 GB | ctx 2,048
  RTX 3080 12GB                      | 4-bit | 87 tok/s       | reported | ttft -ms | vram 9.6 GB | ctx 2,048
  RTX3060+RTX2080-pooled-20GB 20GB   | 4-bit | 118.5 tok/s    | reported | ttft -ms | vram 9.3 GB | ctx 2,048