inferencerlabs
/

MiniMax-M2.5-MLX-Q9

Text Generation

Model card Files Files and versions

MiniMax-M2.5

No longer available on HF due to storage restrictions - archived here

See MiniMax-M2.5 in action: demonstration video

Tested on a M3 Ultra 512GB RAM using Inferencer app v1.10

Single inference ~36.5 tokens/s @ 1000 tokens
Batched inference ~44 total tokens/s across two inferences
Memory usage: ~239 GiB

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for inferencerlabs/MiniMax-M2.5-MLX-Q9

Base model

MiniMaxAI/MiniMax-M2.5

Finetuned

(27)

this model