NexusRaven-V2-13B-4bit-mlx
mlx-community/NexusRaven-V2-13B-4bit-mlx
Uncategorised · mlx
4-bit Open on Hugging Face
Parameters
—
Weights (est.)
—
Mac memory (est.)
—
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.
Details
- Base model
- codellama/CodeLlama-13b-Instruct-hf (finetune)
- Vendor
- codellama
- Task
- Uncategorised
- Quantisation
- 4-bit
- Licence
- other
- Downloads
- 18 in the last 30 days · 276 all time · 0 likes
- Published
- 2024-01-17 · updated 2024-01-17 (2y ago)
- Tags
- llama
Other MLX builds of codellama/CodeLlama-13b-Instruct-hf
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| CodeLlama-13b-Instruct-hf-8bit-mlx | 8-bit | ≈ 13.8 GB | 24 GB+ | 43 |
| NexusRaven-V2-13B-4bit-mlx (this one) | 4-bit | — | — | 18 |