4-bit Open on Hugging Face
Parameters
15B
Weights (est.)
≈ 8.3 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/DeepCoder-14B-Preview-4bit --prompt "Hello"
Details
- Base model
- agentica-org/DeepCoder-14B-Preview (quantized)
- Vendor
- agentica-org
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- mit
- Downloads
- 49 in the last 30 days · 6.1K all time · 2 likes
- Published
- 2025-04-08 · updated 2025-04-08 (1y ago)
- Languages
- en
- Tags
- qwen2
Other MLX builds of agentica-org/DeepCoder-14B-Preview
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| DeepCoder-14B-Preview-4bit (this one) | 4-bit | ≈ 8.3 GB | 16 GB+ | 49 |
| DeepCoder-14B-Preview-6bit | 6-bit | ≈ 12.0 GB | 16 GB+ | 39 |
| DeepCoder-14B-Preview-8bit | 8-bit | ≈ 15.7 GB | 24 GB+ | 56 |
| DeepCoder-14B-Preview-bf16 | bf16 | ≈ 29.5 GB | 48 GB+ | 31 |