6-bit Open on Hugging Face
Parameters
7.6B
Weights (est.)
≈ 6.2 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.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/DiffuCoder-7B-cpGRPO-6bit --prompt "Hello"
Details
- Base model
- apple/DiffuCoder-7B-cpGRPO (quantized)
- Vendor
- apple
- Task
- Text generation
- Quantisation
- 6-bit
- Licence
- unknown
- Downloads
- 27 in the last 30 days · 665 all time · 1 likes
- Published
- 2025-07-04 · updated 2025-07-04 (1y ago)
- Tags
- Dream, code, text-diffusion-model, diffusion large language model, custom_code
Other MLX builds of apple/DiffuCoder-7B-cpGRPO
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| DiffuCoder-7B-cpGRPO-4bit | 4-bit | ≈ 4.3 GB | 8 GB+ | 61 |
| DiffuCoder-7B-cpGRPO-6bit (this one) | 6-bit | ≈ 6.2 GB | 16 GB+ | 27 |
| DiffuCoder-7B-cpGRPO-8bit | 8-bit | ≈ 8.1 GB | 16 GB+ | 74 |