Downloads · 30 days
14
7% of all-time downloads
gemma-3-12b-it-heretic-v2-MLX-Q8
tg-rising/gemma-3-12b-it-heretic-v2-MLX-Q8
gemma-3-12b-it-heretic-v2-MLX-Q8 is a text generation model from tg-rising. Use it when you need the model to write or continue text. It is set up for mlx.
This is a text-only 8-bit MLX-converted version of DreamFast/gemma-3-12b-it-heretic-v2.
All-time downloads
206
Public
Parameters
11.8B
12.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors12.5 GB · 100%
Parameter types
How the weights are stored.
U3211.8B · 100%
Try a prompt
Model card
From the Hugging Face model README
Gemma 3 12B IT Heretic v2 - MLX Q8 (Text-Only)
This is a text-only 8-bit MLX-converted version of DreamFast/gemma-3-12b-it-heretic-v2.
For image understanding, use the VLM variants below!
Source Model
- Original Model: DreamFast/gemma-3-12b-it-heretic-v2
- Base Model: google/gemma-3-12b-it
- Model Type: gemma3
- Parameters: 12B
Model Family
Text-Only Variants (mlx-lm) - This is one of them!
| Variant | Quantization | Size | HF Repo | Use Case |
|---|---|---|---|---|
| BF16 | None | 22 GB | tg-rising/gemma-3-12b-it-heretic-v2-MLX-BF16 | Text generation |
| Q8 | 8-bit | 12 GB | tg-rising/gemma-3-12b-it-heretic-v2-MLX-Q8 | Text generation |
| Q6 | 6-bit | 8.9 GB | tg-rising/gemma-3-12b-it-heretic-v2-MLX-Q6 | Text generation |
| Q4 | 4-bit | 6.2 GB | tg-rising/gemma-3-12b-it-heretic-v2-MLX-Q4 | Text generation |
Vision-Capable Variants (mlx-vlm) - With Image Support!
| Variant | Quantization | Size | HF Repo | Use Case |
|---|---|---|---|---|
| BF16 | None | 25 GB | tg-rising/gemma-3-12b-it-heretic-v2-MLX-VLM-BF16 | Image + Text |
| Q8 | 8-bit | 13 GB | tg-rising/gemma-3-12b-it-heretic-v2-MLX-VLM-Q8 | Image + Text |
| Q6 | 6-bit | 11 GB | tg-rising/gemma-3-12b-it-heretic-v2-MLX-VLM-Q6 | Image + Text |
| Q4 | 4-bit | 7.5 GB | tg-rising/gemma-3-12b-it-heretic-v2-MLX-VLM-Q4 | Image + Text |
Usage
mlx_lm.generate --model tg-rising/gemma-3-12b-it-heretic-v2-MLX-Q8 --prompt "Hello!"
from mlx_lm import load, generate
model, tokenizer = load("tg-rising/gemma-3-12b-it-heretic-v2-MLX-Q8")
prompt = "What is machine learning?"
text = generate(model, tokenizer, prompt=prompt, verbose=True)
Quantization Details
- Bits: 8-bit
- Group Size: 64
- Mode: affine
License
This model is subject to the Gemma license.
- Task
- Text Generation
- Library
- mlx
- Type
- gemma3
- Languages
- en
- Created
- May 25, 2026
- Updated
- May 27, 2026