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/Qwen2.5-72B-Instruct-4bit --prompt "Hello"
Details
- Base model
- Qwen/Qwen2.5-72B-Instruct (quantized)
- Vendor
- Qwen
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- qwen
- Downloads
- 1.0K in the last 30 days · 316K all time · 7 likes
- Published
- 2024-09-18 · updated 2024-09-18 (2y ago)
- Languages
- en
- Tags
- qwen2, chat
Other MLX builds of Qwen/Qwen2.5-72B-Instruct
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Qwen2.5-72B-Instruct-3bit | 3-bit | ≈ 31.8 GB | 48 GB+ | 200 |
| Qwen2.5-72B-Instruct-4bit (this one) | 4-bit | ≈ 40.9 GB | 48 GB+ | 1.0K |
| Qwen2.5-72B-Instruct-4bit-AWQ | 4-bit | ≈ 40.9 GB | 48 GB+ | 57 |
| Qwen2.5-72B-Instruct-6bit | 6-bit | ≈ 59.1 GB | 96 GB+ | 102 |