IBM

Granite 3.3 2B

IBM's compact 2B model. Good at following instructions.

2B parametersgraniteapache-2.08K context1.8GB - 2.6GB VRAM

Check Your Hardware

See which quantizations of Granite 3.3 2B your hardware can run.

Quantization Options

QuantizationBitsFile SizeVRAM NeededRAM NeededQuality
Q4_K_M4.51.3 GB1.8 GB3 GB
85%
Q8_082.1 GB2.6 GB4 GB
98%

See It In Action

Real model outputs generated via RunThisModel.com — watch responses stream in real time.

Llama 3.3 70B responding...

Outputs generated by real AI models via RunThisModel.com. Generation speed shown is from cloud inference. Local speeds vary by hardware — check your device.

Frequently Asked Questions

How much VRAM do I need to run Granite 3.3 2B?

Granite 3.3 2B requires 1.8GB VRAM minimum with Q4_K_M quantization. For full precision, you need 2.6GB VRAM.

What is the best quantization for Granite 3.3 2B?

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