RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can MiMo 7B RL run on the 2x RTX 3090?

Yes. At 8K context the best fit is F16, using about 16.4 GB of the 45.6 GB usable on the 2x RTX 3090. Estimated speed ceiling: ~60 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctxMax tok/s (est., 8K)
2-bit (Q2_K)4.0 GB Fits4.6 GB Fits7.9 GB Fits319
3-bit (Q3_K_M)4.8 GB Fits5.4 GB Fits8.8 GB Fits244
4-bit (Q4_K_M) •5.6 GB Fits6.2 GB Fits9.6 GB Fits200
5-bit (Q5_K_M)6.4 GB Fits7.0 GB Fits10.4 GB Fits168
6-bit (Q6_K) •7.1 GB Fits7.6 GB Fits11.0 GB Fits150
8-bit (Q8_0) •8.8 GB Fits9.4 GB Fits12.7 GB Fits115
16-bit (F16/BF16)15.8 GB Fits16.4 GB Fits19.8 GB Fits60

• real GGUF file size from jedisct1/MiMo-7B-RL-GGUF. Speed is a bandwidth ceiling (936 GB/s), not a benchmark. Methodology.

More

MiMo 7B RL on every GPU and Mac · Every model that runs on the 2x RTX 3090 · Try other settings in the calculator

Data: Hugging Face Hub (XiaomiMiMo/MiMo-7B-RL), NVIDIA specs. Data as of 2026-11-17.