bestmodel.run / model — Qwen3-30B-A3B-Instruct-2507-AWQ-4bit-Q4_K_M-GGUF (agent view)

category chat · cyberjuju/Qwen3-30B-A3B-Instruct-2507-AWQ-4bit-Q4_K_M-GGUF · 1 runs in the model record
answer: 47.8 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
  Radeon RX 7900 XTX 24GB            | 4-bit | 47.8 tok/s     | reported | ttft -ms | vram - GB | ctx 1,024