community pool / model answer

DeepSeek-V4-Flash-0731-GGUF

chat · AtomicChat/DeepSeek-V4-Flash-0731-GGUF

20 tok/s · model median · 2 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 3090 24GB2-bit20 tok/sreported2,444- GB2,048llama.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.