Downloads · 30 days
47
4% of all-time downloads
ronnie3786/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-MLX-4bit
Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-MLX-4bit is a text generation model from ronnie3786. 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.
A 4-bit MLX quantization of Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2, optimized for Apple Silicon.
Downloads · 30 days
47
4% of all-time downloads
All-time downloads
1.1K
Public
Parameters
26.9B
15.2 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors15.1 GB · 100%
How the weights are stored.
U3226.9B · 100%
From the Hugging Face model README
A 4-bit MLX quantization of Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2, optimized for Apple Silicon.
Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2 is the second iteration of the reasoning-focused Qwen3.5-27B fine-tune. It's built on top of Qwen3.5-27B and fine-tuned with Unsloth using distilled reasoning data from Claude 4.6 Opus. This model has been #1 trending on HuggingFace for 3 weeks.
Key improvements in v2:
MLX is Apple's native machine learning framework for Apple Silicon. On an M1 Ultra Mac Studio (128GB), this model runs at 28.9 tokens/sec compared to 19.9 tok/s for the equivalent GGUF Q4_K_M. That's a 45% speed improvement for free, just by using the right format for your hardware.
Controlled test: LM Studio, one model loaded at a time, 10 runs each with different prompts, 512 max tokens.
| Format | Avg tok/s | Std Dev | Min | Max |
|---|---|---|---|---|
| MLX 4-bit | 28.9 | 0.11 | 28.8 | 29.1 |
| GGUF Q4_K_M | 19.9 | 0.03 | 19.9 | 19.9 |
Hardware: M1 Ultra, 128GB unified memory.
Download and place in your LM Studio models directory. LM Studio auto-detects MLX models.
pip install mlx-lm
mlx_lm.generate --model ronnie3786/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-MLX-4bit --prompt "Your prompt here"
mlx_lm.server --model ronnie3786/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-MLX-4bit --port 8080
mlx-lm 0.31.1 via mlx_lm.convertmlx_lm.convert \
--hf-path Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2 \
-q --q-bits 4 \
--mlx-path ./output
Note: Requires mlx-lm >= 0.31.1. Earlier versions don't support the qwen3_5 architecture.