4-bit Open on Hugging Face
Parameters
1.5B
Weights (est.)
≈ 869 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-Coder-1.5B-4bit --prompt "Hello"
Details
- Base model
- Qwen/Qwen2.5-1.5B (finetune)
- Vendor
- Qwen
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 1.3K in the last 30 days · 7.0K all time · 3 likes
- Published
- 2024-09-18 · updated 2024-09-18 (2y ago)
- Languages
- en
- Tags
- qwen2, code, qwen, qwen-coder, codeqwen
Other MLX builds of Qwen/Qwen2.5-1.5B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v1-2bit | 2-bit | ≈ 483 MB | 8 GB+ | 48 |
| Qwen2.5-1.5B-Instruct-4bit | 4-bit | ≈ 869 MB | 8 GB+ | 11K |
| Qwen2.5-Coder-1.5B-4bit (this one) | 4-bit | ≈ 869 MB | 8 GB+ | 1.3K |
| Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v1-4bit | 4-bit | ≈ 869 MB | 8 GB+ | 103 |
| Qwen2.5-Math-1.5B-4bit | 4-bit | ≈ 869 MB | 8 GB+ | 35 |
| Qwen2.5-Coder-1.5B-8bit | 8-bit | ≈ 1.6 GB | 8 GB+ | 227 |
| Qwen2.5-1.5B-Instruct-8bit | 8-bit | ≈ 1.6 GB | 8 GB+ | 145 |
| Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v1-8bit | 8-bit | ≈ 1.6 GB | 8 GB+ | 45 |
| Qwen2.5-Math-1.5B-8bit | 8-bit | ≈ 1.6 GB | 8 GB+ | 38 |
| Qwen2.5-1.5B-Instruct-bf16 | bf16 | ≈ 3.1 GB | 8 GB+ | 298 |
| Qwen2.5-Coder-1.5B-bf16 | bf16 | ≈ 3.1 GB | 8 GB+ | 144 |
| Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v1-f16 | — | ≈ 3.1 GB | 8 GB+ | 44 |
| Qwen2.5-Math-1.5B-bf16 | bf16 | ≈ 3.1 GB | 8 GB+ | 43 |