8-bit Open on Hugging Face
Parameters
1.8B
Weights (est.)
≈ 1.9 GB
Mac memory (est.)
8 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/DeepScaleR-1.5B-Preview-Q8 --prompt "Hello"
Details
- Base model
- agentica-org/DeepScaleR-1.5B-Preview (quantized)
- Vendor
- agentica-org
- Task
- Text generation
- Quantisation
- 8-bit
- Licence
- mit
- Downloads
- 31 in the last 30 days · 466 all time · 1 likes
- Published
- 2025-02-20 · updated 2025-02-20 (1y ago)
- Languages
- en
- Tags
- qwen2
Other MLX builds of agentica-org/DeepScaleR-1.5B-Preview
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| DeepScaleR-1.5B-Preview-4bit | 4-bit | ≈ 1000 MB | 8 GB+ | 35 |
| DeepScaleR-1.5B-6.5bit | 5-bit | ≈ 1.2 GB | 8 GB+ | 44 |
| DeepScaleR-1.5B-Preview-Q8 (this one) | 8-bit | ≈ 1.9 GB | 8 GB+ | 31 |