GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
amd
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
amd
Model Tree
MiniMaxAI/MiniMax-M2.5
Input Modalities
Output Modalities
Supported Functionality
This model can be deployed efficiently using the vLLM and SGLang backends.
The model was evaluated on gsm8k benchmarks using the vllm framework.
The GSM8K result was obtained using the lm-evaluation-harness framework, based on the Docker image rocm/vllm-dev:nightly_main_20260603.
Install the lm-eval (Version: 0.4.12) in container first.
text
pip install lm-evalpip install lm-eval[api]text
VLLM_ROCM_USE_AITER=1 vllm serve amd/MiniMax-M2.5-NVFP4/ \ --tensor-parallel-size 2 \ --tool-call-parser minimax_m2 \ --reasoning-parser minimax_m2 \ --enable-auto-tool-choice \ --trust-remote-codetext
lm_eval \ --model local-completions \ --model_args "model=amd/MiniMax-M2.5-NVFP4/,base_url=http://127.0.0.1:8000/v1/completions,tokenized_requests=False,tokenizer_backend=None,num_concurrent=32" \ --gen_kwargs temperature=1.0,top_p=0.95 \ --tasks gsm8k \ --num_fewshot 8 \ --batch_size 1Modifications Copyright(c) 2026 Advanced Micro Devices, Inc. All rights reserved.