RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Mistral 7B Instruct v0.2 run on the RTX 4080?

Yes. At 8K context the best fit is Q8_0, using about 8.6 GB of the 15.2 GB usable on the RTX 4080. Estimated speed ceiling: ~93 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •29.1 GB No29.6 GB No32.6 GB No—
3-bit (Q3_K_M) •37.6 GB No38.1 GB No41.1 GB No—
4-bit (Q4_K_M) •47.2 GB No47.7 GB No50.7 GB No—
5-bit (Q5_K_M)5.8 GB Fits6.3 GB Fits9.3 GB Fits139
6-bit (Q6_K)6.5 GB Fits7.0 GB Fits10.0 GB Fits121
8-bit (Q8_0)8.1 GB Fits8.6 GB Fits11.6 GB Fits93
16-bit (F16/BF16)14.4 GB Tight14.9 GB Tight17.9 GB No50

• real GGUF file size from bartowski/bigstral-12b-32k-8xMoE-GGUF. Speed is a bandwidth ceiling (717 GB/s), not a benchmark. Methodology.

More

Mistral 7B Instruct v0.2 on every GPU and Mac · Every model that runs on the RTX 4080 · Other models that fit 16 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (mistralai/Mistral-7B-Instruct-v0.2), NVIDIA specs. Data as of 2026-11-17.