Mistral-Large-4-1T-A52B, a 1T-param MoE, lands on Hugging Face
MaziyarPanahi · x · 2026-10-30
Mistral-Large-4-1T-A52B is now on Hugging Face: a 1T-parameter MoE with 52B active parameters, downloadable for local/self-hosted runs. The model card ships a full chat template with tool calling, jsonschema output support, and reasoningeffort controls (default high).
More from Infra
- Intel accelerating clean-room build-outs at Arizona Fab 62, exploring faster Ohio timeline — BenBajarin · 2026-10-30
- Altman says local AI wastes scarce memory; critics say he misses the point — kimmonismus · 2026-10-30
- AI workloads may accelerate the shift from HDDs to all-flash data centers — IBDinvestors · 2026-10-30
- Intel data center revenue jumps 78% to $7.3bn, strongest growth in 15 years — BenBajarin · 2026-10-30
- Backprop-free pretraining hits 4,000x speedup in 10 days, now 1.6 seconds per run — SonglinYang4 · 2026-10-30
- OpenRouter's new router: ~20% faster TTFT, ~60% fewer rate-limit errors for open-weight models — AccBalanced · 2026-10-30