RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Apertus 8B Instruct 2509 run on the RX 7600?

Yes. At 8K context the best fit is Q4_K_M, using about 6.4 GB of the 7.6 GB usable on the RX 7600. Estimated speed ceiling: ~57 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •4.2 GB Fits4.7 GB Fits7.7 GB No88
3-bit (Q3_K_M) •5.0 GB Fits5.5 GB Fits8.5 GB No69
4-bit (Q4_K_M) •5.9 GB Fits6.4 GB Fits9.4 GB No57
5-bit (Q5_K_M) •6.6 GB Fits7.1 GB Tight10.1 GB No50
6-bit (Q6_K) •7.3 GB Tight7.8 GB No10.8 GB No—
8-bit (Q8_0) •9.1 GB No9.6 GB No12.6 GB No—
16-bit (F16/BF16) •16.2 GB No16.7 GB No19.7 GB No—

• real GGUF file size from unsloth/Apertus-8B-Instruct-2509-GGUF. Speed is a bandwidth ceiling (288 GB/s), not a benchmark. Methodology.

More

Apertus 8B Instruct 2509 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 (swiss-ai/Apertus-8B-Instruct-2509), AMD specs. Data as of 2026-11-17.