Kapitsa 0.2.26 Benchmarks: Qwen 35B Hits 346 tok/s on M5 Max
Open-source Apple Silicon inference engine Kapitsa released version 0.2.26, with benchmarks on the M5 Max (128GB) showing Qwen 35B at 346 tok/s and a 180B model running at 61 tok/s on a 48GB Mac via SSD offloading.
2026-11-02 ~ 2026-11-02 · 2 related posts
- Episode 1: Open-source engine kapitsa boosts Mac local LLM inference with tree-based speculative decoding(2026-10-24, 2 posts)
- Episode 2: Kapitsa 0.2.26 Benchmarks: Qwen 35B Hits 346 tok/s on M5 Max(2026-11-02, 2 posts)
- Kapitsa hits 346 tok/s on a 35B MoE and runs a 180B model on 48GB Macs via SSD offloading — DotaMate · 2026-11-02
- Kapitsa inference engine hits 346 tok/s on Qwen 35B, runs 180B via SSD offload on M5 Max — DotaMate · 2026-11-02