IBM

Granite 3.3 8B

IBM's 8B instruction model. Enterprise quality.

8B parametersgraniteapache-2.08K context5.5GB - 9.3GB VRAM

Check Your Hardware

See which quantizations of Granite 3.3 8B your hardware can run.

Quantization Options

QuantizationBitsFile SizeVRAM NeededRAM NeededQuality
Q4_K_M4.54.9 GB5.5 GB8 GB
85%
Q8_088.5 GB9.3 GB12 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 8B?

Granite 3.3 8B requires 5.5GB VRAM minimum with Q4_K_M quantization. For full precision, you need 9.3GB VRAM.

What is the best quantization for Granite 3.3 8B?

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