Downloads · 30 days
105
10% of all-time downloads
gemma-4-12B-coder-fable5-composer2.5-v1-4bit-msq
mlx-community/gemma-4-12B-coder-fable5-composer2.5-v1-4bit-msq
gemma-4-12B-coder-fable5-composer2.5-v1-4bit-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 transformers. The card lists the license as apache-2.0.
Mixed-precision MLX quantization of yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1, quantized with MLX Smart Quantize (MSQ) — my own sensitivity-based mixed-precision quantization method for Apple Silicon. It measur…
All-time downloads
1K
Public
Parameters
12B
7.5 GB on disk
Likes
8
Public
Repo makeup
Click a slice to open those files.
.safetensors7.5 GB · 100%
Parameter types
How the weights are stored.
U3211.9B · 100%
Try a prompt
Base models
Model card
From the Hugging Face model README
gemma-4-12B-coder-fable5-composer2.5-v1 — MLX 4.5 BPW
Mixed-precision MLX quantization of yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1, 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: Vision (VLM)
- Average: 4.5 bits per weight
- Method: MLX Smart Quantize (MSQ)
- AWQ scaling: applied to 96 groups
- Task
- Text Generation
- Library
- transformers
- Type
- gemma4_unified
- License
- apache-2.0
- Created
- Jun 18, 2026
- Updated
- Jun 18, 2026