Meta · open-weights model
Llama-3.2-3B-Instruct
Llama-3.2-3B-Instruct is a 3.2B-parameter model by Meta. Its smallest quant (Q4_K_M) needs at least 3.4GB of GPU-addressable memory at 8K context; it loads cleanly at a quality quant on 50 of the 50 machines we track.
- Parameters
- 3.2B
- Layers
- 28
- Max context
- 128K
- Attention
- GQA
- License
- llama3.2
Config from meta-llama/Llama-3.2-3B-Instruct
Quants and what they need
Measured file sizes; “needs” = weights + KV cache at 8K context + overhead.
| Quant | File size | Needs ≥ |
|---|---|---|
| Q8_0 | 3.4 GB | 4.8 GB |
| Q6_K | 2.6 GB | 4.0 GB |
| Q5_K_M | 2.3 GB | 3.7 GB |
| Q4_K_M | 2.0 GB | 3.4 GB |
What runs Llama-3.2-3B-Instruct
Every machine we track, graded at its best clean-fit quant.
Verdicts computed from published specs and measured GGUF sizes — how the math works.