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/SuperNova-Medius-4bit --prompt "Hello"
Details
- Base model
- arcee-ai/SuperNova-Medius (quantized)
- Vendor
- arcee-ai
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 38 in the last 30 days · 548 all time · 1 likes
- Published
- 2024-10-17 · updated 2024-10-17 (2y ago)
- Tags
- qwen2, mergekit, merge, model-index
Other MLX builds of arcee-ai/SuperNova-Medius
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| SuperNova-Medius-4bit (this one) | 4-bit | ≈ 8.3 GB | 16 GB+ | 38 |
| SuperNova-Medius-8bit | 8-bit | ≈ 15.7 GB | 24 GB+ | 32 |
| SuperNova-Medius-bf16 | bf16 | ≈ 29.5 GB | 48 GB+ | 38 |