RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can diffusiongemma 26B A4B it run on the RX 7900 XT?

Yes. At 8K context the best fit is Q4_K_M, using about 17.1 GB of the 19.0 GB usable on the RX 7900 XT. Estimated speed ceiling: ~307 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 Fits533
3-bit (Q3_K_M)13.0 GB Fits13.2 GB Fits14.1 GB Fits17.8 GB Tight409
4-bit (Q4_K_M) •16.9 GB Fits17.1 GB Fits18.0 GB Tight21.7 GB No307
5-bit (Q5_K_M) •19.1 GB No19.2 GB No20.2 GB No23.9 GB No—
6-bit (Q6_K) •22.4 GB No22.5 GB No23.4 GB No27.2 GB No—
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 (800 GB/s), not a benchmark. Methodology.

More

diffusiongemma 26B A4B it on every GPU and Mac · Every model that runs on the RX 7900 XT · Other models that fit 24 GB VRAM · Try other settings in the calculator

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