antirez ports GLM 5.2 Flash to run on M5 Max, TP across two Macs
antirez · x · 2026-08-28
antirez released GLM 5.2 Flash Q2 and Q4 quantizations, created with a recipe similar to DS4 Flash. It runs on M5 Max with 128GB RAM, and Q4 weights support tensor parallel inference across two M5 Max systems. Testing on CUDA and ROCm is ongoing; code coming to GitHub soon.
Related event: antirez Ports GLM 5.2 Flash to Run Locally on M5 Max(2 posts)→
More from Infra
- SGLang ships Day-0 support for FLUX 3 Image Klein: 10 reference images, BF16/FP8/NVFP4 variants — ying11231 · 2026-10-16
- NVIDIA's Nemotron 3.5 Super VL hits CoreWeave: 12B-active multimodal MoE at $0.25/M input tokens — wandb · 2026-10-16
- Chip equipment beats bull case: 2026 WFE seen at $153B, $278B by 2030 — BenBajarin · 2026-10-16
- Steam now launches in 5.23s, beating Epic's 5.47s — and vLLM gets roasted for slow startup — AlpinDale · 2026-10-16
- Shadeform to Announce Six New Features on Oct 19: Lower GPU Costs, More Suppliers — _jaydeepkarale · 2026-10-16
- Fastino launches Training API for SFT/RL, claiming 25-85% cost cut vs Tinker — kalyan_kpl · 2026-10-16