Remove links to retired duplicate brand variants
Browse files
README.md
CHANGED
|
@@ -114,7 +114,6 @@ This model requires approximately 7 GB of unified memory. Recommended hardware:
|
|
| 114 |
- [google/gemma-4-26B-A4B](https://huggingface.co/google/gemma-4-26B-A4B) -- Base model
|
| 115 |
- [majentik/gemma-4-26B-A4B-RotorQuant-MLX-8bit](https://huggingface.co/majentik/gemma-4-26B-A4B-RotorQuant-MLX-8bit) -- MLX 8-bit variant
|
| 116 |
- [majentik/gemma-4-26B-A4B-RotorQuant-MLX-4bit](https://huggingface.co/majentik/gemma-4-26B-A4B-RotorQuant-MLX-4bit) -- MLX 4-bit variant
|
| 117 |
-
- [majentik/gemma-4-26B-A4B-TurboQuant-MLX-2bit](https://huggingface.co/majentik/gemma-4-26B-A4B-TurboQuant-MLX-2bit) -- TurboQuant MLX 2-bit variant
|
| 118 |
- [RotorQuant GitHub](https://github.com/scrya-com/rotorquant)
|
| 119 |
- [MLX Framework](https://github.com/ml-explore/mlx)
|
| 120 |
|
|
@@ -146,6 +145,3 @@ This model requires approximately 7 GB of unified memory. Recommended hardware:
|
|
| 146 |
| **RotorQuant-MLX-2bit** | mlx-lm | ~8.3 GB | Apple Silicon, smallest |
|
| 147 |
| [RotorQuant-MLX-4bit](https://huggingface.co/majentik/gemma-4-26b-a4b-rotorquant-mlx-4bit) | mlx-lm | ~16 GB | Apple Silicon balanced |
|
| 148 |
| [RotorQuant-MLX-8bit](https://huggingface.co/majentik/gemma-4-26b-a4b-rotorquant-mlx-8bit) | mlx-lm | ~31 GB | Apple Silicon reference |
|
| 149 |
-
| [TurboQuant-MLX-2bit](https://huggingface.co/majentik/gemma-4-26b-a4b-turboquant-mlx-2bit) | mlx-lm | ~8.3 GB | Apple Silicon, smallest |
|
| 150 |
-
| [TurboQuant-MLX-4bit](https://huggingface.co/majentik/gemma-4-26b-a4b-turboquant-mlx-4bit) | mlx-lm | ~16 GB | Apple Silicon balanced |
|
| 151 |
-
| [TurboQuant-MLX-8bit](https://huggingface.co/majentik/gemma-4-26b-a4b-turboquant-mlx-8bit) | mlx-lm | ~31 GB | Apple Silicon reference |
|
|
|
|
| 114 |
- [google/gemma-4-26B-A4B](https://huggingface.co/google/gemma-4-26B-A4B) -- Base model
|
| 115 |
- [majentik/gemma-4-26B-A4B-RotorQuant-MLX-8bit](https://huggingface.co/majentik/gemma-4-26B-A4B-RotorQuant-MLX-8bit) -- MLX 8-bit variant
|
| 116 |
- [majentik/gemma-4-26B-A4B-RotorQuant-MLX-4bit](https://huggingface.co/majentik/gemma-4-26B-A4B-RotorQuant-MLX-4bit) -- MLX 4-bit variant
|
|
|
|
| 117 |
- [RotorQuant GitHub](https://github.com/scrya-com/rotorquant)
|
| 118 |
- [MLX Framework](https://github.com/ml-explore/mlx)
|
| 119 |
|
|
|
|
| 145 |
| **RotorQuant-MLX-2bit** | mlx-lm | ~8.3 GB | Apple Silicon, smallest |
|
| 146 |
| [RotorQuant-MLX-4bit](https://huggingface.co/majentik/gemma-4-26b-a4b-rotorquant-mlx-4bit) | mlx-lm | ~16 GB | Apple Silicon balanced |
|
| 147 |
| [RotorQuant-MLX-8bit](https://huggingface.co/majentik/gemma-4-26b-a4b-rotorquant-mlx-8bit) | mlx-lm | ~31 GB | Apple Silicon reference |
|
|
|
|
|
|
|
|
|