dolphin-2.9.2-qwen2-7b-4bit
mlx-community/dolphin-2.9.2-qwen2-7b-4bit
Uncategorised · mlx
4-bit Open on Hugging Face
Parameters
7.6B
Weights (est.)
≈ 4.3 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
- Qwen/Qwen2-7B (finetune)
- Vendor
- Qwen
- Task
- Uncategorised
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 93 in the last 30 days · 1.0K all time · 3 likes
- Published
- 2024-07-06 · updated 2024-07-06 (2y ago)
- Tags
- qwen2, generated_from_trainer, axolotl
Other MLX builds of Qwen/Qwen2-7B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| dolphin-2.9.2-qwen2-7b-4bit (this one) | 4-bit | ≈ 4.3 GB | 8 GB+ | 93 |
| Molmo-7B-D-0924-3bit | 3-bit | ≈ 4.4 GB | 8 GB+ | 56 |
| Molmo-7B-D-0924-4bit | 4-bit | ≈ 5.3 GB | 8 GB+ | 121 |
| Molmo-7B-D-0924-6bit | 6-bit | ≈ 7.2 GB | 16 GB+ | 58 |
| Molmo-7B-D-0924-8bit | 8-bit | ≈ 9.0 GB | 16 GB+ | 65 |
| Molmo-7B-D-0924-bf16 | bf16 | ≈ 16.0 GB | 24 GB+ | 59 |