Running DeepSeek v4.1 MXFP4 on CPU/NVMe/GPU hybrid: prefill boosted to 960 tok/s
HankYeomans · x · 2026-09-25
A developer ran the 460GB DeepSeek v4.1 MXFP4 quantized model on a CPU/NVMe/GPU hybrid setup, tuning prefill throughput from 216 tok/s to 960 tok/s and decode from 13 tok/s to 42 tok/s. He notes greater efforts exist elsewhere, but this was a hands-on learning project. Next up: end-to-end model creation, optimization and ablation from a base checkpoint.
More from Infra
- Anthropic paid $5B for short-term compute in Q3 as spot prices run ~2x long-term deals — tengyanAI · 2026-11-11
- UK Sovereign AI invests in Fractile to build next-gen frontier AI chips — charlieharris01 · 2026-11-11
- What happened when I moved vector retrieval into Snowflake SQL instead of orchestrating RAG outside — dima806_dima · 2026-11-11
- AI chip startup Fractile raises $720M Series C for DRAM-on-processor design — Tom_Westgarth15 · 2026-11-11
- Mobile AI Factory: agentic pipeline builds on-device SLMs that beat 5-shot frontier models — kalyan_kpl · 2026-11-11
- Vivo's Starlink direct-to-cell service hits 10M users in two weeks across Brazil — XFreeze · 2026-11-11