4-bit Open on Hugging Face
Parameters
73B
Weights (est.)
≈ 40.9 GB
Mac memory (est.)
48 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/Athene-V2-Chat-4bit --prompt "Hello"
Details
- Base model
- Nexusflow/Athene-V2-Chat (quantized)
- Vendor
- Nexusflow
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- other
- Downloads
- 51 in the last 30 days · 407 all time · 1 likes
- Published
- 2024-12-09 · updated 2024-12-09 (1y ago)
- Languages
- en
- Tags
- qwen2, RLHF, Nexusflow, Athene, Chat Model
Other MLX builds of Nexusflow/Athene-V2-Chat
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Athene-V2-Chat-4bit (this one) | 4-bit | ≈ 40.9 GB | 48 GB+ | 51 |
| Athene-V2-Chat-8bit | 8-bit | ≈ 77.3 GB | 96 GB+ | 59 |