Meta · open-weights model
Llama-3.2-1B-Instruct
Llama-3.2-1B-Instruct is a 1.2B-parameter model by Meta. Its smallest quant (Q4_K_M) needs at least 1.5GB of GPU-addressable memory at 8K context; it loads cleanly at a quality quant on 50 of the 50 machines we track.
- Parameters
- 1.2B
- Layers
- 16
- Max context
- 128K
- Attention
- GQA
- License
- llama3.2
Config from meta-llama/Llama-3.2-1B-Instruct
Quants and what they need
Measured file sizes; “needs” = weights + KV cache at 8K context + overhead.
| Quant | File size | Needs ≥ |
|---|---|---|
| Q8_0 | 1.3 GB | 2.0 GB |
| Q6_K | 1.0 GB | 1.7 GB |
| Q5_K_M | 0.9 GB | 1.6 GB |
| Q4_K_M | 0.8 GB | 1.5 GB |
What runs Llama-3.2-1B-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.