RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Llama 3.2 11B Vision run on the RX 7600?

Yes. At 8K context the best fit is Q3_K_M, using about 6.7 GB of the 7.6 GB usable on the RX 7600. Estimated speed ceiling: ~55 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K)5.0 GB Fits5.6 GB Fits9.4 GB No24.4 GB No72
3-bit (Q3_K_M)6.1 GB Fits6.7 GB Fits10.5 GB No25.5 GB No55
4-bit (Q4_K_M)7.3 GB Tight8.0 GB No11.7 GB No26.7 GB No—
5-bit (Q5_K_M)8.3 GB No9.0 GB No12.7 GB No27.7 GB No—
6-bit (Q6_K)9.4 GB No10.0 GB No13.8 GB No28.8 GB No—
8-bit (Q8_0)11.8 GB No12.4 GB No16.2 GB No31.2 GB No—
16-bit (F16/BF16)21.1 GB No21.7 GB No25.5 GB No40.5 GB No—

• real GGUF file size. Speed is a bandwidth ceiling (288 GB/s), not a benchmark. Methodology.

More

Llama 3.2 11B Vision on every GPU and Mac · Every model that runs on the RX 7600 · Other models that fit 8 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (meta-llama/Llama-3.2-11B-Vision), AMD specs. Data as of 2026-11-17.