RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Molmo2 4B run on the RTX 5080?

Yes. At 8K context the best fit is F16, using about 10.0 GB of the 15.2 GB usable on the RTX 5080. Estimated speed ceiling: ~109 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctxMax tok/s (est., 8K)
2-bit (Q2_K)2.9 GB Fits3.5 GB Fits6.9 GB Fits528
3-bit (Q3_K_M)3.5 GB Fits4.0 GB Fits7.4 GB Fits405
4-bit (Q4_K_M) •3.8 GB Fits4.3 GB Fits7.7 GB Fits353
5-bit (Q5_K_M)4.5 GB Fits5.0 GB Fits8.4 GB Fits278
6-bit (Q6_K)5.0 GB Fits5.5 GB Fits8.9 GB Fits241
8-bit (Q8_0) •5.6 GB Fits6.2 GB Fits9.6 GB Fits205
16-bit (F16/BF16) •9.5 GB Fits10.0 GB Fits13.4 GB Fits109

• real GGUF file size from reubk/Molmo2-4B-GGUF. Speed is a bandwidth ceiling (960 GB/s), not a benchmark. Methodology.

More

Molmo2 4B on every GPU and Mac · Every model that runs on the RTX 5080 · Other models that fit 16 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (allenai/Molmo2-4B), NVIDIA specs. Data as of 2026-11-17.