NVIDIA ships NIM deployment recipes for Mistral Large 4 on Blackwell FP8/NVFP4
NVIDIAAI · x · 2026-11-06
NVIDIA announced that Mistral Large 4 can be deployed via downloadable NVIDIA NIM containers, with recipes for Blackwell (FP8, NVFP4) and Vera Rubin (FP8). Docs describe the model as a vision-language MoE with tool calling and a 1,048,576-token context window, using the experimental vLLM Model-Free NIM; minimum stack: Ubuntu 22.04, CUDA 12.9, driver 580+, Docker 24+.
More from Infra
- Only 2% of PC gamers own an RTX 5080 or 5090, Steam data shows — ssh4net · 2026-11-06
- SOX plunges 12.2%, worst day since March 2020, as AI trade gets repriced — tengyanAI · 2026-11-06
- Replit's custom kernel sandbox dodged 96% of 6,211 audited Linux CVEs — amasad · 2026-11-06
- Eigen AI founder on inference economics: cheaper tokens expand the whole market — songhan_mit · 2026-11-06
- DFlash 2 parallel drafting lifts speculative decoding acceptance 21% for 1.3% latency cost — songhan_mit · 2026-11-06
- Pre-training done in 68 hours with 4-bit used all the way from pre- to post-training — teortaxesTex · 2026-11-06