MTPLX V2 Released: Runs Qwen 27B on MacBook M5 Max at 72+ Tokens/sec
awnihannun · x · 2026-07-08
MTPLX V2 has been released, a local inference tool based on the MLX framework and optimized specifically for Apple Silicon. In real-world testing, running Qwen 3.6 27B on a MacBook Pro M5 Max achieved 72+ tokens/sec. The author claims this is currently the fastest way to run models on MLX.
Related event: MTPLX V2 Boosts Local Mac LLM Inference to 80+ TPS(2 posts)→
More from Infra
- RTK Terminal Compression Cuts Tokens but Leaves Your AI Coding Bill Unchanged — Bartaseth · 2026-09-11
- SF Compute founder: buying compute is 'an absolutely awful experience' right now — IgorCarron · 2026-09-11
- SmolVM open-sources persistent computer infrastructure for agents that outlive chat sessions — aniketmaurya · 2026-09-11
- PyTorch Day Korea 2026 launches first offline conf, CFP closes Sept 13 — PyTorch · 2026-09-11
- Local LLM server dilemma: 4x CMP-170HX (price up 53% in 20 days) vs Mac Studio M5 Ultra — rumboll · 2026-09-11
- llama.cpp lands Flash Attention tuning for RDNA4, big prefill gains on AMD — pmttyji · 2026-09-11