DwarfStar Runs Lossless MXFP4 DeepSeek Locally on M3 Ultra
antirez · x · 2026-08-01
antirez shared an update on his open-source project DwarfStar: a new branch now runs the lossless MXFP4 DeepSeek v4 Flash GGUF locally on a single M3 Ultra at 31 tokens/s. It also achieves >20 t/s on 128GB systems using SSD streaming.
Related event: antirez's DwarfStar Enables Local Lossless DeepSeek Inference(3 posts)→
More from Infra
- Reflection's 501B MoE Beam hits 463 tok/s on 8x GB200 with NVFP4 at day 0 — zhyncs42 · 2026-10-16
- Nemotron 3.5 Bolt runs 16 concurrent streams on a single DGX Spark — NVIDIAAI · 2026-10-16
- Why your computer can't store 0.2: an IEEE 754 primer — Franc0Fernand0 · 2026-10-16
- Sabaki: MIT-licensed typed decision router runs on CPU in milliseconds — Fox3000foxy · 2026-10-16
- BitRun v0.2 runs 8B ternary LLMs on CPU in 2GB RAM with live wattage telemetry — The_VibePreneur · 2026-10-16
- MiniCPM-V 4.5 MoE reportedly hits 13+ tokens/s on iPhone with just 3GB memory — heyshrutimishra · 2026-10-16