Qwen2.5-Math-72B-Instruct-bf16
mlx-community/Qwen2.5-Math-72B-Instruct-bf16
Text generation · transformers
bf16 Open on Hugging Face
Parameters
73B
Weights (est.)
≈ 145 GB
Mac memory (est.)
192 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-Math-72B-Instruct-bf16 --prompt "Hello"
Details
- Base model
- Qwen/Qwen2.5-Math-72B (finetune)
- Vendor
- Qwen
- Task
- Text generation
- Quantisation
- bf16
- Licence
- qwen
- Downloads
- 30 in the last 30 days · 523 all time · 0 likes
- Published
- 2024-09-18 · updated 2024-09-19 (2y ago)
- Languages
- en
- Tags
- qwen2, chat
Other MLX builds of Qwen/Qwen2.5-Math-72B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Qwen2.5-Math-72B-Instruct-8bit | 8-bit | ≈ 77.3 GB | 96 GB+ | 53 |
| Qwen2.5-Math-72B-Instruct-bf16 (this one) | bf16 | ≈ 145 GB | 192 GB+ | 30 |