GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
fanwu103
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
fanwu103
Model Tree
Base
XiaomiMiMo/MiMo-V2.5-Pro
Quantized
this model
Input Modalities
Text
Audio
Image
Video
Output Modalities
Text
Supported Functionality
Dedicated Endpoints
*.experts.*.{gate,up,down}_proj) and dense MLPs (layers.0.mlp.*)This model was built from MiMo-V2.5-Pro by applying AMD-Quark for MXFP4 quantization. All attention layers (*self_attn*), the MoE router (*mlp.gate), the LM head, embeddings, norms, and the MTP layers (*mtp.layers*) are excluded from MXFP4.
The model was quantized directly from the source FP8 release at XiaomiMiMo/MiMo-V2.5-Pro using AMD-Quark in --file2file_quantization mode (per-shard streaming, no full-model materialization). Both weights and activations of the targeted layers are quantized to MXFP4.
bash
cd Quark/examples/torch/language_modeling/llm_ptq/exclude_layers="*self_attn* *mlp.gate *mlp.gate.linear *lm_head *embed_tokens* *norm* *mtp.layers*"python quantize_quark.py \--model_dir /path/to/MiMo-V2.5-Pro \--quant_scheme mxfp4 \--exclude_layers $exclude_layers \--output_dir amd/MiMo-V2.5-Pro-MXFP4 \--model_export hf_format \--file2file_quantization
This model can be deployed efficiently using the vLLM backend.
The model was evaluated on GSM8K.
| Benchmark | MiMo-V2.5-Pro (FP8) | MiMo-V2.5-Pro-MXFP4 (this model) | Recovery |
|---|---|---|---|
| GSM8K (flexible-extract) ↑ | 0.9424 | 0.9424 | 100.0% |
| GSM8K (strict-match) ↑ | 0.9416 | 0.9409 | 99.9% |
The results above were obtained using the lm-evaluation-harness framework, with vLLM and amd-quark compiled and installed from source.
bash
lm_eval \--model vllm \--model_args pretrained=amd/MiMo-V2.5-Pro-MXFP4,trust_remote_code=True,tensor_parallel_size=8,dtype=auto,gpu_memory_utilization=0.9,max_model_len=4096,enforce_eager=False \--tasks gsm8k \--num_fewshot 5 \--batch_size auto
This model is a quantized derivative of XiaomiMiMo/MiMo-V2.5-Pro and is released under the same MIT license as the upstream model.
Modifications Copyright (c) 2026 Advanced Micro Devices, Inc. All rights reserved.