GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
EmbeddedLLM
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
EmbeddedLLM
Model Tree
MiniMaxAI/MiniMax-M3
Input Modalities
Output Modalities
Supported Functionality
This model is an FP8 dynamic quantized version of MiniMaxAI/MiniMax-M3.
MiniMaxAI/MiniMax-M3MiniMax-M3 is a native multimodal MoE model. The original model card describes it as a ~428B parameter model with ~23B activated parameters and 1M context support.
This quantized checkpoint follows the license terms of the base model, MiniMaxAI/MiniMax-M3. The Hugging Face model-card metadata uses license: other because the MiniMax community license is not one of the Hub's enumerated license identifiers.
This checkpoint uses FP8 dynamic quantization to reduce memory and disk requirements while preserving model quality. Validation below compares this quantized checkpoint against the BF16 MiniMaxAI/MiniMax-M3 baseline.
The model was evaluated against BF16 MiniMaxAI/MiniMax-M3. Scores are averaged across seeds.
| Benchmark | MiniMaxAI/MiniMax-M3 | EmbeddedLLM/MiniMax-M3-FP8-dynamic | Recovery (%) |
|---|---|---|---|
| GSM8k Platinum | 95.81 | 95.92 | 100.12 |
| IfEval | 80.65 | 79.42 | 98.47 |
| AIME 2025 | 20.83 | 19.17 | 92.00 |
| GPQA diamond | 77.78 | 77.95 | 100.22 |
42, 1234, 415842, 1234, 4158, 5322, 1356, 9843, 3344, 5678max_gen_toks=64000max_gen_toks=4096max_gen_toks=2048| Math 500 | 81.20 | 79.93 | 98.44 |
| Lcb Codegeneration V6 | 37.14 | 35.62 | 95.90 |
| MMLU Pro Chat | 79.85 | 79.62 | 99.72 |