Downloads · 30 days
67
5% of all-time downloads
AITRADER/Jackrong-Qwen3.5-4B-Claude-Reasoning-abliterated-mxfp8-MLX
Jackrong-Qwen3.5-4B-Claude-Reasoning-abliterated-mxfp8-MLX is a text generation model from AITRADER. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as apache-2.0.
This is an abliterated (uncensored) and MXFP8 quantized version of Jackrong/Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled, converted to MLX format for Apple Silicon.
Downloads · 30 days
67
5% of all-time downloads
All-time downloads
1.3K
Public
Parameters
4.5B
15 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors10.7 GB · 100%
How the weights are stored.
U324.2B · 93%
From the Hugging Face model README
This is an abliterated (uncensored) and MXFP8 quantized version of Jackrong/Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled, converted to MLX format for Apple Silicon.
The base model is Qwen3.5-4B fine-tuned on Claude 4.6 Opus reasoning data using Unsloth/LoRA, giving it strong chain-of-thought reasoning capabilities. This abliterated version removes safety refusal behaviors while preserving the model's reasoning abilities. MXFP8 quantization reduces model size by ~48% with minimal quality loss.
Qwen3.5 hybrid attention architecture:
pip install mlx-lm
# Generate text
mlx_lm.generate --model AITRADER/Jackrong-Qwen3.5-4B-Claude-Reasoning-abliterated-mxfp8-MLX --prompt "Explain quantum computing"
from mlx_lm import load, generate
model, tokenizer = load("AITRADER/Jackrong-Qwen3.5-4B-Claude-Reasoning-abliterated-mxfp8-MLX")
response = generate(model, tokenizer, prompt="Your prompt here", max_tokens=512)
A bf16 full-precision version (~7.9 GB) is available at: AITRADER/Jackrong-Qwen3.5-4B-Claude-Reasoning-abliterated-fp16-MLX
This model is provided for research purposes. Users are responsible for ensuring their use complies with applicable laws and regulations.