8-bit Open on Hugging Face
Parameters
8.8B
Weights (est.)
≈ 10.0 GB
Mac memory (est.)
16 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Details
- Base model
- HiDream-ai/HiDream-O1-Image-Dev (finetune)
- Vendor
- HiDream-ai
- Task
- Text to image
- Quantisation
- 8-bit
- Licence
- mit
- Downloads
- 51 in the last 30 days · 950 all time · 2 likes
- Published
- 2026-05-10 · updated 2026-05-11 (6mo ago)
- Languages
- en
- Tags
- qwen3_vl, mlx-vlm, hidream, apple-silicon, quantized, q8
Other MLX builds of HiDream-ai/HiDream-O1-Image-Dev
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| HiDream-O1-Image-Dev-mlx-q6 | 6-bit | ≈ 8.0 GB | 16 GB+ | 72 |
| HiDream-O1-Image-Dev-mlx-q8 (this one) | 8-bit | ≈ 10.0 GB | 16 GB+ | 51 |
| HiDream-O1-Image-Dev-mlx-bf16 | bf16 | ≈ 17.5 GB | 24 GB+ | 281 |