Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -15,6 +15,9 @@ pipeline_tag: text-to-image
|
|
| 15 |
|
| 16 |
# MLX Nucleus-Image
|
| 17 |
|
|
|
|
|
|
|
|
|
|
| 18 |
An [MLX](https://github.com/ml-explore/mlx) port of [NucleusAI/Nucleus-Image](https://huggingface.co/NucleusAI/Nucleus-Image) — a **17B parameter Mixture-of-Experts DiT** for text-to-image generation, running natively on Apple Silicon.
|
| 19 |
|
| 20 |
17B total parameters, ~2B active per token. 32 transformer layers (3 dense + 29 MoE), 64 routed experts + 1 shared per layer, expert-choice routing. GQA attention with 16 query / 4 KV heads. Text conditioning via Qwen3-VL-8B.
|
|
@@ -106,3 +109,7 @@ Hybrid port — text encoding stays in PyTorch, everything else runs in MLX:
|
|
| 106 |
- Source code: [github.com/treadon/mlx-nucleus-image](https://github.com/treadon/mlx-nucleus-image)
|
| 107 |
- [Apple MLX](https://github.com/ml-explore/mlx)
|
| 108 |
- Built by [@treadon](https://x.com/treadon)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
|
| 16 |
# MLX Nucleus-Image
|
| 17 |
|
| 18 |
+
|
| 19 |
+
> Follow [**@treadon on X**](https://x.com/treadon) and [**treadon on Hugging Face**](https://huggingface.co/treadon) for more AI experiments, evals, and projects.
|
| 20 |
+
|
| 21 |
An [MLX](https://github.com/ml-explore/mlx) port of [NucleusAI/Nucleus-Image](https://huggingface.co/NucleusAI/Nucleus-Image) — a **17B parameter Mixture-of-Experts DiT** for text-to-image generation, running natively on Apple Silicon.
|
| 22 |
|
| 23 |
17B total parameters, ~2B active per token. 32 transformer layers (3 dense + 29 MoE), 64 routed experts + 1 shared per layer, expert-choice routing. GQA attention with 16 query / 4 KV heads. Text conditioning via Qwen3-VL-8B.
|
|
|
|
| 109 |
- Source code: [github.com/treadon/mlx-nucleus-image](https://github.com/treadon/mlx-nucleus-image)
|
| 110 |
- [Apple MLX](https://github.com/ml-explore/mlx)
|
| 111 |
- Built by [@treadon](https://x.com/treadon)
|
| 112 |
+
|
| 113 |
+
## More from me
|
| 114 |
+
|
| 115 |
+
For other projects and writeups, see [**riteshkhanna.com**](https://riteshkhanna.com), follow [**@treadon on X**](https://x.com/treadon), or [**treadon on Hugging Face**](https://huggingface.co/treadon).
|