RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Kimi K2 Instruct 0905 run on the RTX 4060?

No. Even at 2-bit with 8K context, Kimi K2 Instruct 0905 needs about 350 GB, more than the 7.6 GB usable on the RTX 4060.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •349 GB No350 GB No351 GB No358 GB No—
3-bit (Q3_K_M) •457 GB No458 GB No459 GB No466 GB No—
4-bit (Q4_K_M) •580 GB No580 GB No581 GB No588 GB No—
5-bit (Q5_K_M) •680 GB No680 GB No682 GB No688 GB No—
6-bit (Q6_K) •786 GB No786 GB No788 GB No794 GB No—
8-bit (Q8_0) •1017 GB No1017 GB No1019 GB No1025 GB No—
16-bit (F16/BF16) •1913 GB No1913 GB No1915 GB No1921 GB No—

• real GGUF file size from unsloth/Kimi-K2-Instruct-0905-GGUF. Speed is a bandwidth ceiling (272 GB/s), not a benchmark. Methodology.

Hardware that does fit it

Mac M3 Ultra 512GB

More

Kimi K2 Instruct 0905 on every GPU and Mac · Every model that runs on the RTX 4060 · Other models that fit 8 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (moonshotai/Kimi-K2-Instruct-0905), NVIDIA specs. Data as of 2026-11-17.