Meta
Llama 3.2 1B Instruct
Ultra-compact 1B model. Runs on virtually any device including smartphones.
1.24B parametersllamallama3.2128K context1.3GB - 1.8GB VRAM
Check Your Hardware
See which quantizations of Llama 3.2 1B Instruct your hardware can run.
Quantization Options
| Quantization | Bits | File Size | VRAM Needed | RAM Needed | Quality |
|---|---|---|---|---|---|
| Q4_K_M | 4.5 | 0.8 GB | 1.3 GB | 2 GB | 85% |
| Q8_0 | 8 | 1.3 GB | 1.8 GB | 3 GB | 98% |
Frequently Asked Questions
How much VRAM do I need to run Llama 3.2 1B Instruct?
Llama 3.2 1B Instruct requires 1.3GB VRAM minimum with Q4_K_M quantization. For full precision, you need 1.8GB VRAM.
What is the best quantization for Llama 3.2 1B Instruct?
Q4_K_M offers the best balance of quality and VRAM usage. Q8_0 is near-lossless if you have enough VRAM.