GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
The-JDdev
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
The-JDdev
Model Tree
Base
MiniMaxAI/MiniMax-M3
Fine-tuned
this model
Input Modalities
Text
Image
Video
Output Modalities
Text
Supported Functionality
Dedicated Endpoints
☕ If these models are useful to you, consider supporting my work — it funds compute for more & larger abliterations.
💬 Discord: discord.gg/rhUZY5GEZr · ₿ Bitcoin: bc1qsvfduzj9fjs9fugpc52yver3f2g8fp7xjxecdv
This is an abliterated (uncensored) build of MiniMaxAI/MiniMax-M3 — the full bfloat16 weights with the model's refusal behavior removed, while keeping its reasoning, multilingual, coding, and multimodal abilities intact. Legitimate safety and security-analysis engagement is preserved, as is tool use — the model simply stops reflexively refusing.
MiniMax-M3 is a large multimodal Mixture-of-Experts model with a vision tower and a built-in reasoning ("thinking") mode. The architecture, tokenizer, and chat template are unchanged, so this is a drop-in replacement for the base model.
Serve with vLLM (a MiniMax-M3-capable build is required):
bash
MODEL=OpenYourMind/Minimax-M3-abliterated-cleanvllm serve "$MODEL" \--tensor-parallel-size 8 \--block-size 128 \--reasoning-parser minimax_m3 \--tool-call-parser minimax_m3 \--enable-auto-tool-choice
The model wraps its reasoning in <mm:think> … </mm:think>; use the minimax_m3 reasoning parser to surface it. --block-size 128 is required for MiniMax Sparse Attention.
| File | Description |
|---|---|
model-*-of-00059.safetensors | BF16 weights — text backbone + MoE experts + vision tower |
config.json, configuration_minimax_m3_vl.py, image_processor.py | Model config + processor |
tokenizer*, merges.txt, chat_template.jinja, generation_config.json | Tokenizer + chat template |
Total on disk: ~854 GB (bfloat16).
These are full BF16 weights — plan for a multi-GPU / multi-node deployment (e.g. 8×/16× 80 GB-class accelerators), or quantize (NVFP4 / MXFP4 / FP8) to fit smaller setups. Quantized builds may follow.
Use is the responsibility of the user. Ensure your usage complies with applicable laws, platform rules, and deployment requirements.