community pool / model answer

DeepSeek-V4-Flash-0731-MXFP4-GGUF

chat · Rabbit-Hole-Ai/DeepSeek-V4-Flash-0731-MXFP4-GGUF

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

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 5090 32GB4-bit26.4 tok/sreported3,05528.3 GB196,608llama.cpp

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.