Antirez publishes a mixed q2/q3 Laguna S2.1 quant for 64GB MacBooks
antirez · x · 2026-07-24
Antirez says he has published mixed q2/q3 quantizations of Laguna S2.1 that run on 64GB MacBook systems with quality close to q4.
- Requires either the DwarfStar laguna-s2.1 branch or llama.cpp.
- Reported performance: 65 tok/s generation and about 570 tok/s prefill with DwarfStar.
- The model is described as an interesting specialized coding model and, according to the post, the first of its kind to fit on 64GB machines.
Related event: antirez releases Laguna S2.1 hybrid quantization(2 posts)→
More from coding & agent
- Alex Townsend posts 200 open problems in numerical linear algebra for humans and AI agents — IgorCarron · 2026-09-11
- Kimi K2.8 Preview rolls out: near-K3 coding performance, 1M context for all tiers — teortaxesTex · 2026-09-11
- Looking for a classifier of software engineering task shapes to pick models per task — StewartalsopIII · 2026-09-11
- Steal this idea: prompt-to-hardware where agents assemble custom devices — paraschopra · 2026-09-11
- Model Is the Least Interesting Part: A Guide to Six Core AI Architectures from RAG to Multi-Agent — goyalshaliniuk · 2026-09-11
- Non-coder builds layered memory architecture: 20k tokens tracks a year of agent conversations — matteoianni · 2026-09-11