Dwarfstar on 128GB M5 Max Mac Studio hits 16 tok/s with SSD offload via DeepSeek Flash 4.1
antirez · x · 2026-10-19
Developer prasincs tested antirez's Dwarfstar on a 128GB M5 Max Mac Studio running DeepSeek Flash 4.1, achieving 16 tok/s output with SSD offload — roughly 3x more than what would fit in memory alone, a data point for running oversized models on large-RAM Macs.
More from Infra
- vLLM 0.32.0 adds structured-decision API reading first-token probabilities — AccBalanced · 2026-10-19
- GPU pricing is now set by cost of capital, not spot rates, argues Maya — AccBalanced · 2026-10-19
- Liquid Inference ships DeepSeek V4.1-Flash support, ComfyUI plugin over weekend — AccBalanced · 2026-10-19
- Analyst revises 2027 datacenter forecast up to +50GW, citing satellite imagery — AccBalanced · 2026-10-19
- Cisco and NVIDIA unveil USFP optical module plan: 4x bandwidth density — shashib · 2026-10-19
- Hyperscaler capex shifting from chip vendors to in-house silicon by 2027, investor argues — pdamodaran · 2026-10-19