GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
gauravmm
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
gauravmm
Model Tree
MiniMaxAI/MiniMax-M2
Input Modalities
Output Modalities
Supported Functionality
bash
vllm serve gauravmm/MiniMax-M2.5-REAP-139B-A10B-NVFP4 \ --quantization compressed-tensors \ --moe-backend marlin \ --trust-remote-code \ --max-model-len 65536 \ --kv-cache-dtype fp8
--moe-backend marlinis mandatory on this NVFP4 W4A16 checkpoint — the flashinfer_cutlass MoE backend rejects W4A16 NVFP4 and crashes engine-core init.
MiniMax-M2 (MiniMax AI, modified-MIT) → REAP prune (Cerebras) → NVFP4 W4A16 (this repo).
License inherited from upstream (see LICENSE): MIT with a high-revenue attribution clause
(display "MiniMax M2" if the deploying product exceeds the stated annual-recurring-revenue
threshold).