4-bit Open on Hugging Face
Parameters
24B
Weights (est.)
≈ 13.3 GB
Mac memory (est.)
24 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/ether0-4bit --prompt "Hello"
Details
- Base model
- futurehouse/ether0 (quantized)
- Vendor
- futurehouse
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 32 in the last 30 days · 193 all time · 0 likes
- Published
- 2025-06-06 · updated 2025-06-06 (1y ago)
- Languages
- en
- Tags
- mistral, smiles, chemistry, reasoning
Other MLX builds of futurehouse/ether0
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| ether0-4bit (this one) | 4-bit | ≈ 13.3 GB | 24 GB+ | 32 |
| ether0-8bit | 8-bit | ≈ 25.0 GB | 32 GB+ | 32 |
| ether0-bf16 | bf16 | ≈ 94.3 GB | 128 GB+ | 25 |