Homegrown inference engine runs Xiaomi's 1T-parameter model at 1300 tok/s
bookwormengr · x · 2026-09-30
In a reply, @bingxu claims their in-house generated inference engine can run Xiaomi's 1T-parameter model at 1300 tokens per second, with a demo video attached. If accurate, that would be a striking throughput for such a massive MoE model, though no implementation details or hardware specs are disclosed in the post.
More from Infra
- India's Sarvam launches Token Factory, hosting top open models on local infra — HarveenChadha · 2026-11-16
- ZGX Fury stress-tested: 351 tok/s on Qwen3.8-Flash-Next, offline agents and local RAG demos — Sam Witteveen · 2026-11-16
- Gemini 3.5 Flash now runs on air-gapped Google Distributed Cloud, offline up to 12 months — shashib · 2026-11-16
- Gemma.c: full Gemma 1/2/3 multimodal inference in a single C file, ~72 tok/s on CPU at INT8 — This-Purchase-3325 · 2026-11-16
- BIS Issues Interim Final Rule Addressing Remote Access to Advanced AI Chips — apples_jimmy · 2026-11-16
- Jailbroken PS4 runs a 9B open-source model at up to 43 tok/s by talking directly to its 2013-era GPU — AIFlow_ML · 2026-11-16