bf16 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/Qwen2.5-0.5B-Instruct-bf16 --prompt "Hello"
Details
- Base model
- Qwen/Qwen2.5-0.5B (finetune)
- Vendor
- Qwen
- Task
- Text generation
- Quantisation
- bf16
- Licence
- apache-2.0
- Downloads
- 1.8K in the last 30 days · 42K all time · 1 likes
- Published
- 2024-09-18 · updated 2024-09-18 (2y ago)
- Languages
- en
- Tags
- qwen2, chat
Other MLX builds of Qwen/Qwen2.5-0.5B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Qwen2.5-0.5B-Instruct-4bit | 4-bit | ≈ 278 MB | 8 GB+ | 27K |
| Qwen2.5-0.5B-Instruct-8bit | 8-bit | ≈ 525 MB | 8 GB+ | 177 |
| VibeVoice-Realtime-0.5B-4bit | 4-bit | ≈ 633 MB | 8 GB+ | 135 |
| VibeVoice-Realtime-0.5B-5bit | 5-bit | ≈ 754 MB | 8 GB+ | 20 |
| VibeVoice-Realtime-0.5B-6bit | 6-bit | ≈ 876 MB | 8 GB+ | 22 |
| Qwen2.5-0.5B-Instruct-bf16 (this one) | bf16 | ≈ 988 MB | 8 GB+ | 1.8K |
| VibeVoice-Realtime-0.5B-8bit | 8-bit | ≈ 1.1 GB | 8 GB+ | 254 |
| VibeVoice-Realtime-0.5B-fp16 | fp16 | ≈ 2.0 GB | 8 GB+ | 377 |