No official torrent yet — requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from dealignai/MiniMax-M2.5-UNCENSORED-JANG_2L
All models by dealignai →Important: This model uses the JANG quantization format — the GGUF equivalent for MLX on Apple Silicon. Currently only supported by MLX Studio and the
jang-toolsPython package.
JANG mixed-precision · CRACK abliterated · No guardrails · 63 GB
This is MiniMax M2.5 — a 230B parameter Mixture-of-Experts model with 256 experts (8 active per token), all standard attention (no SSM), and trained with chain-of-thought reasoning.
It has been:
MLX uniform quantization is completely broken on MiniMax at ALL bit levels (~25% = random chance). JANG is the only working quantization format for this model.
Safety guardrails were actively degrading the model's reasoning ability. CRACK surgery unlocked the model's full capacity for mathematical and logical reasoning.
314/320 (98.1%) — tested with enable_thinking=false, temperature=1.0
Note: MiniMax generates a
<think>chain before answering by default. To disable thinking, passenable_thinking=Falsein your chat template kwargs. Usemax_tokens=2000+for complex questions. For chat applications, usetemperature=1.0(greedy causes loops).
JANG (Jang Adaptive N-bit Grading) is a mixed-precision quantization format for Apple Silicon — the GGUF equivalent for MLX. Classifies tensors into sensitivity tiers and assigns bits accordingly.
CRACK (Controlled Refusal Ablation via Calibrated Knockouts) removes safety alignment from LLMs at the weight level using per-layer projected vectors from structurally-mirrored prompt pairs.
This model is provided for research and educational purposes. The creators are not responsible for any misuse. By downloading this model, you agree to use it responsibly and in compliance with applicable laws.
GitHub · HuggingFace · MLX Studio · Ko-fi · X @dealignai
Created by Jinho Jang · 장진호 제작
pip install "jang[mlx]"from jang_tools.loader import load_jang_modelfrom mlx_lm import generate
model, tokenizer = load_jang_model("dealignai/MiniMax-M2.5-JANG_2L-CRACK")
messages = [{"role": "user", "content": "Your prompt here"}]prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=False)
response = generate(model, tokenizer, prompt=prompt, max_tokens=2000)print(response)pip install "jang[mlx]"