Mistral AI

Mistral 7B Instruct v0.3

Efficient 7B model from Mistral AI with strong performance for its size.

7.3B parametersmistralapache-2.032K context4.57GB - 15.5GB VRAM

Check Your Hardware

See which quantizations of Mistral 7B Instruct v0.3 your hardware can run.

Quantization Options

QuantizationBitsFile SizeVRAM NeededRAM NeededQuality
Q4_K_M4.54.072 GB4.57 GB5.07 GB
85%
Q5_K_M5.54.783 GB5.28 GB5.78 GB
90%
Q8_087.174 GB7.67 GB8.17 GB
98%
FP161614.5 GB15.5 GB18 GB
100%

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 Mistral 7B Instruct v0.3?

Mistral 7B Instruct v0.3 requires 4.57GB VRAM minimum with Q4_K_M quantization. For full precision, you need 15.5GB VRAM.

What is the best quantization for Mistral 7B Instruct v0.3?

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