RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can diffusiongemma 26B A4B it run on the RTX 4090?

Yes. At 8K context the best fit is Q5_K_M, using about 19.2 GB of the 22.8 GB usable on the RTX 4090. Estimated speed ceiling: ~340 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K)10.3 GB Fits10.4 GB Fits11.4 GB Fits15.1 GB Fits672
3-bit (Q3_K_M)13.0 GB Fits13.2 GB Fits14.1 GB Fits17.8 GB Fits516
4-bit (Q4_K_M) •16.9 GB Fits17.1 GB Fits18.0 GB Fits21.7 GB Tight387
5-bit (Q5_K_M) •19.1 GB Fits19.2 GB Fits20.2 GB Fits23.9 GB No340
6-bit (Q6_K) •22.4 GB Tight22.5 GB Tight23.4 GB No27.2 GB No287
8-bit (Q8_0) •26.3 GB No26.4 GB No27.4 GB No31.1 GB No—
16-bit (F16/BF16) •48.3 GB No48.5 GB No49.4 GB No53.2 GB No—

• real GGUF file size from unsloth/diffusiongemma-26B-A4B-it-GGUF. Speed is a bandwidth ceiling (1008 GB/s), not a benchmark. Methodology.

More

diffusiongemma 26B A4B it on every GPU and Mac · Every model that runs on the RTX 4090 · Other models that fit 24 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (google/diffusiongemma-26B-A4B-it), NVIDIA specs. Data as of 2026-11-17.