tinygrad hits ~200 tok/s MiMo-V2.6-Pro on MI300X, brought up via GLM-5.3
AIFlow_ML · x · 2026-09-23
tinygrad reports bringing up MiMo-V2.6-Pro on an AMD MI300X (with GLM-5.3 assisting the bring-up), reaching roughly 200 tok/s. It highlights continued tinygrad optimization for AMD hardware and strong large-model inference performance outside the NVIDIA ecosystem.
More from Infra
- Leaked Alibaba roadmap: Qwen 5 to scale to 5-10 trillion parameters — burny_tech · 2026-09-23
- Hugging Face Transformers now runs llama.cpp GGUF quants natively — ariG23498 · 2026-09-23
- Goldman: US to Outspend China $806B to $110B on AI Infra in 2026, China Fights Back on Efficiency — FinanceYF5 · 2026-09-23
- Nokia Signs Four Cloud Data Deals in 90 Days, But Its AI-RAN Bet Rests on One Chipmaker — shashib · 2026-09-23
- China Weighs Curbs on Broadcom Switches Behind Up to 90% of State Data Centers — rohanpaul_ai · 2026-09-23
- Rumors: 64GB+ VRAM RTX 5090 in R&D but not coming anytime soon — AIFlow_ML · 2026-09-23