community pool / model answer

DeepSeek-V4-Flash-Vision-Exp

chat · deepseek-ai/DeepSeek-V4-Flash-Vision-Exp

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

Answer

179.5tok/s

reportedRTX PRO 6000 Blackwell 96GB ×28-bit · 1 run · decodebest cell in the pool

  1. RTX PRO 6000 Blackwell 96GB ×2179.5 tok/sreported1 run · peak 183.1 GB · fits 192 GB rig memory
Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX PRO 6000 Blackwell 96GB ×28-bit179.5 tok/sreported121183.1 GB1,048,576vllm

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.