8-bit Open on Hugging Face
Parameters
73B
Weights (est.)
≈ 77.3 GB
Mac memory (est.)
96 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/EVA-Qwen2.5-72B-v0.0-8bit --prompt "Hello"
Details
- Base model
- EVA-UNIT-01/EVA-Qwen2.5-72B-v0.0 (quantized)
- Vendor
- EVA-UNIT-01
- Task
- Text generation
- Quantisation
- 8-bit
- Licence
- qwen
- Downloads
- 32 in the last 30 days · 497 all time · 0 likes
- Published
- 2024-10-31 · updated 2024-10-31 (2y ago)
- Tags
- qwen2, generated_from_trainer
Other MLX builds of EVA-UNIT-01/EVA-Qwen2.5-72B-v0.0
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| EVA-Qwen2.5-72B-v0.0-8bit (this one) | 8-bit | ≈ 77.3 GB | 96 GB+ | 32 |
| EVA-Qwen2.5-72B-v0.0 | — | ≈ 145 GB | 192 GB+ | 51 |