community pool / model answer

Qwen3.5-9B-TT-BFP4-P150

chat · Lottolabs/Qwen3.5-9B-TT-BFP4-P150

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

Answer

76.2tok/s

reportedTenstorrent P150 32GB4-bit · 1 run · decodebest cell in the pool

  1. Tenstorrent P150 32GB76.2 tok/sreported1 run · peak VRAM no data yet · 32 GB rig memory
Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
Tenstorrent P150 32GB4-bit76.2 tok/sreported209- GB8,192vllm

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.