Downloads · 30 days
7
6% of all-time downloads
Gemma-4-26B-A4B-it-MLX-8bit
pipenetwork/Gemma-4-26B-A4B-it-MLX-8bit
Gemma-4-26B-A4B-it-MLX-8bit is a text generation model from pipenetwork. 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.
MLX (Apple Silicon) conversion of google/gemma-4-26B-A4B-it (Mixture-of-Experts, ~4B active), quantized to 8-bit · near-lossless. Text-only build.
All-time downloads
119
Public
Parameters
25.2B
26.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors26.8 GB · 100%
Parameter types
How the weights are stored.
U3225.2B · 100%
Try a prompt
Base models
Model card
From the Hugging Face model README
Gemma-4-26B-A4B-it-MLX-8bit
MLX (Apple Silicon) conversion of google/gemma-4-26B-A4B-it (Mixture-of-Experts, ~4B active), quantized to 8-bit · near-lossless. Text-only build.
Quantizations
Part of the Gemma-4-26B-A4B-it MLX collection.
| Variant | Notes |
|---|---|
| 4-bit | 4-bit · community build (mlx-community) |
| 8-bit (this repo) | 8-bit · near-lossless |
| 6-bit | 6-bit · high quality |
| 5-bit | 5-bit |
Use with mlx-lm
pip install mlx-lm
python -m mlx_lm generate --model pipenetwork/Gemma-4-26B-A4B-it-MLX-8bit --prompt "Explain Mixture-of-Experts briefly." -m 256
Validation
Smoke-tested locally: loads and generates coherent text.
License
Apache 2.0 (inherited from base). Quantization config: {"group_size": 64, "bits": 8, "mode": "affine", "language_model.model.layers.0.router.proj": {"group_size": 64, "bits": 8}, "language_model.model.layers.1.router.proj": {"group_size": 64, "bits": 8}, .
- Task
- Text Generation
- Library
- mlx
- Type
- gemma4
- License
- apache-2.0
- Created
- Jun 14, 2026
- Updated
- Jun 14, 2026