GLM-5.2 NVFP4 Inference Speedup
nickcraske · x · 2026-07-10
A cited source reveals that GLM-5.2 has achieved inference optimization on Nvidia NVFP4 without pruning or quantization, retaining the same model card and delivering 110 tok/s in a single stream. The quote also mentions a repo reproducing Full DS4-Flash running at 38.5 tok/s on a 5090 + DDR5 setup, which the author calls a breakthrough.
More from Infra
- Gavin Baker argues Nvidia may be one of open source AI’s biggest supporters — GavinSBaker · 2026-07-22
- AI Power Demand Exposes US Energy Gap, Urging Shift from Scarcity to Abundance — bradneuberg · 2026-07-22
- Gavin Baker says Nvidia’s $630B figure would be system revenue, not all Nvidia’s — GavinSBaker · 2026-07-22
- A Firecracker-based platform says it can host 6,000 AI agents on one 256 GB server — maritime_sh · 2026-07-22
- Report says Nvidia could build 1,000 Vera Rubin racks a day, implying $630B quarterly at system level — GavinSBaker · 2026-07-22
- oMLX 0.5.2 adds Mac menu-bar stats, low-bit decode kernels, and faster downloads — awnihannun · 2026-07-22