bestmodel.run / model — SmolLM2-135M-Instruct-GGUF (agent view)

category chat · unsloth/SmolLM2-135M-Instruct-GGUF · 2 runs in the model record
answer: 1,052.6 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 5090 32GB                      | 2-bit | 1,102.1 tok/s  | reported | ttft 7ms | vram - GB | ctx 2,048
  RTX 5090 32GB                      | 4-bit | 1,003.1 tok/s  | reported | ttft 8ms | vram - GB | ctx 2,048