fp16 Open on Hugging Face
Parameters
494M
Weights (est.)
≈ 988 MB
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.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/QwQ-0.5B-fp16 --prompt "Hello"
Details
- Base model
- InfiniAILab/QwQ-0.5B (finetune)
- Vendor
- InfiniAILab
- Task
- Text generation
- Quantisation
- fp16
- Licence
- —
- Downloads
- 16 in the last 30 days · 327 all time · 0 likes
- Published
- 2025-04-07 · updated 2025-04-07 (1y ago)
- Tags
- qwen2
Other MLX builds of InfiniAILab/QwQ-0.5B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| QwQ-0.5B-4bit | 4-bit | ≈ 278 MB | 8 GB+ | 28 |
| QwQ-0.5B-6bit | 6-bit | ≈ 401 MB | 8 GB+ | 31 |
| QwQ-0.5B-8bit | 8-bit | ≈ 525 MB | 8 GB+ | 17 |
| QwQ-0.5B-fp16 (this one) | fp16 | ≈ 988 MB | 8 GB+ | 16 |