RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Kimi VL A3B Thinking run on the 2x RTX 5090?

Yes. At 8K context the best fit is F16, using about 31.5 GB of the 60.8 GB usable on the 2x RTX 5090. Estimated speed ceiling: ~299 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K)6.6 GB Fits6.7 GB Fits7.4 GB Fits10.2 GB Fits1593
3-bit (Q3_K_M)8.3 GB Fits8.4 GB Fits9.1 GB Fits12.0 GB Fits1222
4-bit (Q4_K_M)10.2 GB Fits10.3 GB Fits11.0 GB Fits13.8 GB Fits977
5-bit (Q5_K_M)11.7 GB Fits11.8 GB Fits12.5 GB Fits15.4 GB Fits838
6-bit (Q6_K)13.4 GB Fits13.5 GB Fits14.2 GB Fits17.0 GB Fits728
8-bit (Q8_0)17.1 GB Fits17.2 GB Fits17.9 GB Fits20.7 GB Fits562
16-bit (F16/BF16)31.4 GB Fits31.5 GB Fits32.2 GB Fits35.1 GB Fits299

• real GGUF file size. Speed is a bandwidth ceiling (1792 GB/s), not a benchmark. Methodology.

More

Kimi VL A3B Thinking on every GPU and Mac · Every model that runs on the 2x RTX 5090 · Try other settings in the calculator

Data: Hugging Face Hub (moonshotai/Kimi-VL-A3B-Thinking), NVIDIA specs. Data as of 2026-11-17.