community pool / model answer

Ling-3.0-flash-int4

chat · inclusionAI/Ling-3.0-flash-int4

37.3 tok/s · model median · 1 runs in the model record.

Answer

37.3tok/s

reportedGB10 Grace Blackwell 128GB4-bit · 1 run · decodebest cell in the pool

  1. GB10 Grace Blackwell 128GB · unified memory37.3 tok/sreported1 run · peak VRAM no data yet
Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
GB10 Grace Blackwell 128GB4-bit37.3 tok/sreported-- GB131,072vllm

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.