Qwen3.8-Flash-Next NVFP4 hits 184 tok/s on a single RTX 6000 Pro
matteohorvath · hn · 2026-10-27
Mesh Applied published a blog post demonstrating Qwen3.8-Flash-Next running in NVFP4 quantization at 184 tok/s on a single RTX 6000 Pro, showcasing the throughput potential of 4-bit floating point formats for local LLM inference on workstation GPUs. Details in their release blog post.
More from Infra
- Critical pre-boot RCE in EDK II PXE driver: one crafted packet hijacks servers before Secure Boot — cyb3rops · 2026-10-28
- Screenless M1 Airs at $30 per 1,000 multicore points spark cheap Mac cluster idea — vincent_koc · 2026-10-28
- RTX 3080 Tensor Core unlock claims 80-87% TFLOPS boost, RTX 50 series blocked — Revolutionalredstone · 2026-10-28
- CXMT to start small-scale HBM3E production within two months, yield at 20% — zephyr_z9 · 2026-10-28
- Video Transcription Costs Under 1 Yuan per Hour, CPU Free but Error-Prone — huangyun_122 · 2026-10-28
- A forgotten supercomputer design: bare dies, gold post interconnects, 3D stacking, immersion cooling — jwt0625 · 2026-10-28