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-M2.1
Input Modalities
Output Modalities
Supported Functionality
The model was quantized from QuixiAI/MiniMax-M2.1-bf16 using AMD-Quark. The weights are quantized to MXFP4 and activations are quantized to MXFP4.
Quantization scripts:
markdown
cd Quark/examples/torch/language_modeling/llm_ptq/export exclude_layers="lm_head *block_sparse_moe.gate* *self_attn*"python3 quantize_quark.py --model_dir $MODEL_DIR \--quant_scheme mxfp4 \--num_calib_data 128 \--exclude_layers $exclude_layers \--skip_evaluation \--multi_gpu \--trust_remote_code \--model_export hf_format \--output_dir $output_dir
For further details or issues, please refer to the AMD-Quark documentation or contact the respective developers.
The model was evaluated on gsm8k benchmarks using the vllm framework.
The GSM8K results were obtained using the vLLM framework, based on the Docker image rocm/vllm-dev:nightly_main_20260211, and vLLM is installed inside the container.
To download the evaluation script, reinstallation is not required.
markdown
# Install vLLM code repogit clone https://github.com/vllm-project/vllm.gitcd vllmgit checkout v0.13.0cd ..
markdown
VLLM_ROCM_USE_AITER=1 \VLLM_DISABLE_COMPILE_CACHE=1 \vllm serve "$MODEL" \--tensor-parallel-size 4 \--trust-remote-code \--max-model-len 32768 \--port 8899
markdown
python vllm/tests/evals/gsm8k/gsm8k_eval.py --host http://127.0.0.1 --port 8899 --num-questions 1000 --save-results logs
Modifications Copyright(c) 2026 Advanced Micro Devices, Inc. All rights reserved.