Dolphin3.0-Llama3.1-8B-4bit
mlx-community/Dolphin3.0-Llama3.1-8B-4bit
Uncategorised · mlx
4-bit Open on Hugging Face
Parameters
8.0B
Weights (est.)
≈ 4.5 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.
Details
- Base model
- dphn/Dolphin3.0-Llama3.1-8B (quantized)
- Vendor
- dphn
- Task
- Uncategorised
- Quantisation
- 4-bit
- Licence
- llama3.1
- Downloads
- 284 in the last 30 days · 22K all time · 0 likes
- Published
- 2025-01-05 · updated 2025-01-05 (1y ago)
- Languages
- en
- Tags
- llama
Other MLX builds of dphn/Dolphin3.0-Llama3.1-8B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Dolphin3.0-Llama3.1-8B-MLX-4bit | 4-bit | ≈ 4.5 GB | 8 GB+ | 766 |
| Dolphin3.0-Llama3.1-8B-4bit (this one) | 4-bit | ≈ 4.5 GB | 8 GB+ | 284 |
| Dolphin3.0-Llama3.1-8B-MLX-6bit | 6-bit | ≈ 6.5 GB | 16 GB+ | 276 |
| Dolphin3.0-Llama3.1-8B-6bit | 6-bit | ≈ 6.5 GB | 16 GB+ | 44 |
| Dolphin3.0-Llama3.1-8B-8bit | 8-bit | ≈ 8.5 GB | 16 GB+ | 88 |
| Dolphin3.0-Llama3.1-8B-bf16 | bf16 | ≈ 16.1 GB | 24 GB+ | 57 |