dolphin-2.9.1-qwen-110b-2bit
mlx-community/dolphin-2.9.1-qwen-110b-2bit
Uncategorised · mlx
2-bit Open on Hugging Face
Parameters
111B
Weights (est.)
≈ 34.8 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.
Details
- Base model
- Qwen/Qwen1.5-110B (finetune)
- Vendor
- Qwen
- Task
- Uncategorised
- Quantisation
- 2-bit
- Licence
- other
- Downloads
- 27 in the last 30 days · 411 all time · 1 likes
- Published
- 2024-05-12 · updated 2024-05-12 (2y ago)
- Tags
- qwen2, generated_from_trainer, axolotl
Other MLX builds of Qwen/Qwen1.5-110B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| dolphin-2.9.1-qwen-110b-2bit (this one) | 2-bit | ≈ 34.8 GB | 48 GB+ | 27 |
| dolphin-2.9.1-qwen-110b-4bit | 4-bit | ≈ 62.6 GB | 96 GB+ | 25 |
| dolphin-2.9.1-qwen-110b-8bit | 8-bit | ≈ 118 GB | 192 GB+ | 19 |