6250.0 tokens/s prompt processing (prefill)Prompt processing measures input prefill speed; it does not tell you the time to first token.
Quant
NVFP4 (GGUF)
VRAM reported
32 GB
Summary
User benchmarks a new NVFP4 quant of Qwen3.8 27B on an RTX 5090.
The quant includes a quantized MTP draft head.
User reports it is 50% faster than a Q4 quant and 4-7% faster than other NVFP4 quants.