antirez shows DeepSeek v4 Flash vision running fast locally on an M5 Max; Metal/CUDA/ROCm support nearly ready
antirez · x · 2026-09-01
antirez (creator of Redis) demoed the experimental vision variant of DeepSeek v4 Flash running fast locally on an Apple M5 Max machine, analyzing an image. He says the Metal / CUDA / ROCm implementation is finished and he's doing last tests today before releasing it.
More from Infra
- Anthropic commits $80B to cloud capacity in a single month — kimmonismus · 2026-09-01
- ESP32 voice assistant: 8x wake-word model compression with AIMET — carrycooldude · 2026-09-01
- LITE plans VCSEL products for AI interconnects, delayed by 1-2 years — zephyr_z9 · 2026-09-01
- Xiaohongshu & NVIDIA build GR-Inference engine, doubling throughput for Beam Search — 小红书技术REDtech · 2026-09-01
- Nvidia Earnings: Avoiding Consolidation and Dollars per Gigawatt — Stratechery · 2026-09-01
- Sats4AI Offers Bitcoin-Powered AI Tools via Lightning Network — modelcontextprotocol · 2026-09-01