ReZero-v0.1-llama-3.2-3b-it-grpo-250404-4bit
mlx-community/ReZero-v0.1-llama-3.2-3b-it-grpo-250404-4bit
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/ReZero-v0.1-llama-3.2-3b-it-grpo-250404-4bit --prompt "Hello"
Details
- Base model
- Menlo/ReZero-v0.1-llama-3.2-3b-it-grpo-250404 (quantized)
- Vendor
- Menlo
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- —
- Downloads
- 36 in the last 30 days · 3.2K all time · 0 likes
- Published
- 2025-04-16 · updated 2025-04-16 (1y ago)
- Languages
- en
- Tags
- llama
Other MLX builds of Menlo/ReZero-v0.1-llama-3.2-3b-it-grpo-250404
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| ReZero-v0.1-llama-3.2-3b-it-grpo-250404-4bit (this one) | 4-bit | ≈ 1.8 GB | 8 GB+ | 36 |
| ReZero-v0.1-llama-3.2-3b-it-grpo-250404-6bit | 6-bit | ≈ 2.6 GB | 8 GB+ | 25 |
| ReZero-v0.1-llama-3.2-3b-it-grpo-250404-8bit | 8-bit | ≈ 3.4 GB | 8 GB+ | 30 |
| ReZero-v0.1-llama-3.2-3b-it-grpo-250404-fp16 | fp16 | ≈ 6.4 GB | 16 GB+ | 27 |