RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can gemma 4 26B A4B it run on the RX 9070?

Yes. At 8K context the best fit is Q3_K_M, using about 13.3 GB of the 15.2 GB usable on the RX 9070. Estimated speed ceiling: ~324 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 Tight427
3-bit (Q3_K_M) •13.1 GB Fits13.3 GB Fits14.2 GB Tight17.9 GB No324
4-bit (Q4_K_M) •17.0 GB No17.2 GB No18.1 GB No21.9 GB No—
5-bit (Q5_K_M) •20.9 GB No21.1 GB No22.0 GB No25.8 GB No—
6-bit (Q6_K) •22.8 GB No23.0 GB No23.9 GB No27.7 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 No48.4 GB No49.4 GB No53.1 GB No—

• real GGUF file size from unsloth/gemma-4-26B-A4B-it-GGUF. Speed is a bandwidth ceiling (640 GB/s), not a benchmark. Methodology.

More

gemma 4 26B A4B it on every GPU and Mac · Every model that runs on the RX 9070 · Other models that fit 16 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (google/gemma-4-26B-A4B-it), AMD specs. Data as of 2026-11-17.