Downloads · 30 days
330
10% of all-time downloads
RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx-4bit-msq
mlx-community/RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx-4bit-msq
RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx-4bit-msq is a text generation model from mlx-community. 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.
Mixed-precision MLX quantization of deadbydawn101/RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx, quantized with MLX Smart Quantize (MSQ) — my own sensitivity-based mixed-precision…
All-time downloads
3.4K
Public
Parameters
34.7B
21.7 GB on disk
Likes
4
Trending 1
Repo makeup
Click a slice to open those files.
.safetensors21.7 GB · 100%
Parameter types
How the weights are stored.
U3234.6B · 100%
Try a prompt
Base models
Model card
From the Hugging Face model README
RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx — MLX 4.5 BPW
Mixed-precision MLX quantization of deadbydawn101/RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx, quantized with MLX Smart Quantize (MSQ) — my own sensitivity-based mixed-precision quantization method for Apple Silicon. It measures per-layer NMSE and assigns optimal bit widths automatically, combining architecture knowledge with measured data.
Details
- Type: Text (LLM)
- Average: 4.50 bits per weight
- Method: MLX Smart Quantize (MSQ)
- AWQ scaling: applied to 50 groups
- Task
- Text Generation
- Library
- mlx
- Type
- qwen3_5_moe
- License
- apache-2.0
- Languages
- en
- Created
- Jun 18, 2026
- Updated
- Jun 18, 2026