FreeToken Claims Faster MoE Inference vs. llama.cpp and Ollama
wavefnx · x · 2026-08-18
FreeToken claims to serve Mixture-of-Experts (MoE) models significantly faster than popular alternatives like llama.cpp, ktransformers, ollama, or moe-infinity. The associated paper was released yesterday, though independent benchmarks are not yet available. While a binary is available, the source code has been taken down, and the author advises against running the binary without reverse engineering it first.
Related event: FreeToken: Edge-Native Engine Runs 290B MoE Models on Consumer Hardware(4 posts)→
More from Infra
- Large data centers employ only ~50-150 permanent on-site staff, Microsoft says — brezina · 2026-10-16
- Prediction: Opus 5.5-level models on laptops by 2027, backed by Qwen 27B data — cephaloform · 2026-10-16
- Oracle down 12% in a week, nearly 50% off June high as OpenAI exposure spooks market — alvelda · 2026-10-16
- US data center moratoriums top 400 — an AI bull explains why they're actually good for AI — kevinsxu · 2026-10-16
- Microsoft Research unveils Magnetar, the fastest zkVM at 10-39x speedups and post-quantum security — jedisct1 · 2026-10-16
- Bonsai 2 2B hits 120 tok/s on iPhone 18 Pro, outpaces Qwen 3.5 2B at half the memory — cephaloform · 2026-10-16