Josiefied-Hermes-3-Llama-3.2-3B-v1-4bit
mlx-community/Josiefied-Hermes-3-Llama-3.2-3B-v1-4bit
Text generation · mlx
4-bit Open on Hugging Face
Parameters
3.2B
Weights (est.)
≈ 1.8 GB
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-Hermes-3-Llama-3.2-3B-v1-4bit --prompt "Hello"
Details
- Base model
- Goekdeniz-Guelmez/Josiefied-Hermes-3-Llama-3.2-3B-v1 (quantized)
- Vendor
- Goekdeniz-Guelmez
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- —
- Downloads
- 61 in the last 30 days · 360 all time · 0 likes
- Published
- 2025-10-28 · updated 2025-10-28 (1y ago)
- Tags
- llama, chat
Other MLX builds of Goekdeniz-Guelmez/Josiefied-Hermes-3-Llama-3.2-3B-v1
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Josiefied-Hermes-3-Llama-3.2-3B-v1-4bit (this one) | 4-bit | ≈ 1.8 GB | 8 GB+ | 61 |
| Josiefied-Hermes-3-Llama-3.2-3B-v1-6bit | 6-bit | ≈ 2.6 GB | 8 GB+ | 46 |
| Josiefied-Hermes-3-Llama-3.2-3B-v1-8bit | 8-bit | ≈ 3.4 GB | 8 GB+ | 62 |
| Josiefied-Hermes-3-Llama-3.2-3B-v1-bf16 | bf16 | ≈ 6.4 GB | 16 GB+ | 33 |