← CanIRunLocal · All hardware · All models
MiniMax · 428B parameters · chat, reasoning, coding, vision.
Ollama lists minimax-m3.1-flash:cloud as a cloud model. Open weights are announced but not yet downloadable, so there is no local setup command.
Ollama lists this as a cloud model (ollama run minimax-m3.1-flash:cloud, 428B parameters, 976K context, text and image). Open weights were announced for 2026-10-23 and are not on Hugging Face yet, so there is no local download.
No listed GPU, Mac, or multi-node cluster has enough fast memory for the verified weights.
None of the listed machines have enough fast memory.
Estimates, not benchmarks. Model sizes are ollama.com download sizes; memory needed adds headroom for ~8k tokens of context; speeds are rough figures from memory bandwidth. Data updated 2026-10-20.
A project by OnDevice Labs · llms.txt