RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can DeepSeek OCR run on the RX 7600?

Yes. At 8K context the best fit is F16, using about 6.6 GB of the 7.6 GB usable on the RX 7600. Estimated speed ceiling: ~143 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctxMax tok/s (est., 8K)
2-bit (Q2_K)2.0 GB Fits2.3 GB Fits673
3-bit (Q3_K_M)2.4 GB Fits2.6 GB Fits516
4-bit (Q4_K_M) •2.7 GB Fits2.9 GB Fits432
5-bit (Q5_K_M)3.1 GB Fits3.3 GB Fits354
6-bit (Q6_K)3.4 GB Fits3.7 GB Fits308
8-bit (Q8_0) •3.8 GB Fits4.0 GB Fits269
16-bit (F16/BF16) •6.4 GB Fits6.6 GB Fits143

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

More

DeepSeek OCR 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 (deepseek-ai/DeepSeek-OCR), AMD specs. Data as of 2026-11-17.