RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can LLaDA2.1 mini run on the 2x RTX 5090?

Yes. At 8K context the best fit is F16, using about 31.3 GB of the 60.8 GB usable on the 2x RTX 5090. Estimated speed ceiling: ~625 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctxMax tok/s (est., 8K)
2-bit (Q2_K)6.5 GB Fits6.7 GB Fits7.6 GB Fits3335
3-bit (Q3_K_M)8.3 GB Fits8.4 GB Fits9.3 GB Fits2559
4-bit (Q4_K_M)10.1 GB Fits10.3 GB Fits11.2 GB Fits2046
5-bit (Q5_K_M)11.6 GB Fits11.8 GB Fits12.7 GB Fits1755
6-bit (Q6_K)13.3 GB Fits13.4 GB Fits14.4 GB Fits1525
8-bit (Q8_0)16.9 GB Fits17.1 GB Fits18.0 GB Fits1177
16-bit (F16/BF16)31.1 GB Fits31.3 GB Fits32.2 GB Fits625

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

More

LLaDA2.1 mini on every GPU and Mac · Every model that runs on the 2x RTX 5090 · Try other settings in the calculator

Data: Hugging Face Hub (inclusionAI/LLaDA2.1-mini), NVIDIA specs. Data as of 2026-11-17.