RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can MiMo V2.6 Flash RL run on the RTX 6000 Ada?

No. Even at 2-bit with 8K context, MiMo V2.6 Flash RL needs about 110 GB, more than the 45.6 GB usable on the RTX 6000 Ada.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K)110 GB No110 GB No114 GB No127 GB No—
3-bit (Q3_K_M)143 GB No143 GB No147 GB No160 GB No—
4-bit (Q4_K_M)178 GB No179 GB No182 GB No196 GB No—
5-bit (Q5_K_M)207 GB No208 GB No211 GB No225 GB No—
6-bit (Q6_K)239 GB No239 GB No243 GB No256 GB No—
8-bit (Q8_0)309 GB No309 GB No313 GB No326 GB No—
16-bit (F16/BF16)580 GB No581 GB No584 GB No598 GB No—

• real GGUF file size. Speed is a bandwidth ceiling (960 GB/s), not a benchmark. Methodology.

Hardware that does fit it

H200Mac M2 Ultra 192GBMac M3 Ultra 256GBMac M3 Ultra 512GB

More

MiMo V2.6 Flash RL on every GPU and Mac · Every model that runs on the RTX 6000 Ada · Other models that fit 48 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (XiaomiMiMo/MiMo-V2.6-Flash-RL), NVIDIA specs. Data as of 2026-11-17.