antirez runs DeepSeek v4.1 Flash on a single M5 Max 128GB with 800 t/s prefill
antirez · x · 2026-09-11
antirez details running DeepSeek v4.1 Flash (Q2) locally on a single M5 Max 128GB: the loader takes just 8 seconds to go from SSD-streamed experts cache to fully resident encoder (50%) blocks that fit comfortably in memory, at which point prefill reaches 800 tokens/s. He notes this is what the DwarfStart startup process leverages.
More from Infra
- Anthropic's noncancelable compute commitments hit $430B, per S-1 filing — Hesamation · 2026-10-27
- AI chip startup Tenstorrent raises $1.5B at $6.2B valuation, more than doubling — Beth_Kindig · 2026-10-27
- Anthropic discloses up to $120.5B SpaceX compute deal, ~$3.1B monthly at full capacity — XFreeze · 2026-10-27
- Satire: swapping Raft for an LLM-style decision model tanks write throughput 99.98% — irombie · 2026-10-27
- Cadence joins the domain-specific AI model camp for chip design — karlfreund · 2026-10-27
- Qdrant builds Universal I/O to run vector search mmap code on object storage — qdrant_engine · 2026-10-27