Meta

Llama 3.2 3B Instruct

Meta's compact 3B model designed for edge and mobile deployment.

3.2B parametersllamallama3.2128K context2.6GB - 4GB VRAM

Check Your Hardware

See which quantizations of Llama 3.2 3B Instruct your hardware can run.

Quantization Options

QuantizationBitsFile SizeVRAM NeededRAM NeededQuality
Q4_K_M4.52 GB2.6 GB4 GB
85%
Q5_K_M5.52.4 GB3 GB4 GB
90%
Q8_083.4 GB4 GB6 GB
98%

Frequently Asked Questions

How much VRAM do I need to run Llama 3.2 3B Instruct?

Llama 3.2 3B Instruct requires 2.6GB VRAM minimum with Q4_K_M quantization. For full precision, you need 4GB VRAM.

What is the best quantization for Llama 3.2 3B Instruct?

Q4_K_M offers the best balance of quality and VRAM usage. Q8_0 is near-lossless if you have enough VRAM.