FreeToken framework claims major MoE inference speedups
wavefnx · x · 2026-08-18
FreeToken is a new framework claiming to serve MoE models significantly faster than llama.cpp, ktransformers, or Ollama. The paper was released yesterday; while binaries are available, the code has been taken down. The framework reportedly uses 'double buffers' for checkpointing, but performance verification awaits reverse engineering or code re-release.
Related event: FreeToken: Edge-Native Engine Runs 290B MoE Models on Consumer Hardware(4 posts)→
More from Infra
- Musk says he wants 'maybe more than 10GW' of compute; Nvidia now counts SpaceX as a CSP and co-designs a space server — elonmusk · 2026-10-16
- Jensen Huang: Musk's AI buildout moved from K's to M's, now a CSP-tier NVIDIA customer — elonmusk · 2026-10-16
- EpochAI pegs GPT-6 training at up to 1.8e27 FLOP; scaling01 calls param estimates way too high — scaling01 · 2026-10-16
- Meta's Muse Spark Open scores 39 vs 48 for closed Spark 1.3 on AA Intelligence Index — EAccelerate_42 · 2026-10-16
- LLM spots useless 95GB-per-frame memcpy in ffmpeg dblur, cutting runtime from 2452ms to 49ms — IgorCarron · 2026-10-16
- DeepSeek-V4-Flash on 4x Radeon AI PRO R9700: the 'refused' 4-card config hits ~79 tok/s — brainchillzZ · 2026-10-16