Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1-4bit
mlx-community/Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1-4bit
Text generation · mlx
4-bit Open on Hugging Face
Parameters
494M
Weights (est.)
≈ 278 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/Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1-4bit --prompt "Hello"
Details
- Base model
- Goekdeniz-Guelmez/Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1 (quantized)
- Vendor
- Goekdeniz-Guelmez
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 64 in the last 30 days · 4.6K all time · 0 likes
- Published
- 2024-11-17 · updated 2024-11-17 (2y ago)
- Languages
- en, de
- Tags
- qwen2, chat
Other MLX builds of Goekdeniz-Guelmez/Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1-4bit (this one) | 4-bit | ≈ 278 MB | 8 GB+ | 64 |
| Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1-8bit | 8-bit | ≈ 525 MB | 8 GB+ | 53 |
| Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1 | — | ≈ 988 MB | 8 GB+ | 107 |
| Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1-float16 | — | ≈ 988 MB | 8 GB+ | 44 |
| Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1-float32 | — | ≈ 2.0 GB | 8 GB+ | 109 |