RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can DeepSeek OCR run on the RTX 4070?

Yes. At 8K context the best fit is F16, using about 6.6 GB of the 11.4 GB usable on the RTX 4070. Estimated speed ceiling: ~251 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctxMax tok/s (est., 8K)
2-bit (Q2_K)2.0 GB Fits2.3 GB Fits1178
3-bit (Q3_K_M)2.4 GB Fits2.6 GB Fits904
4-bit (Q4_K_M) •2.7 GB Fits2.9 GB Fits756
5-bit (Q5_K_M)3.1 GB Fits3.3 GB Fits620
6-bit (Q6_K)3.4 GB Fits3.7 GB Fits539
8-bit (Q8_0) •3.8 GB Fits4.0 GB Fits471
16-bit (F16/BF16) •6.4 GB Fits6.6 GB Fits251

• real GGUF file size from sabafallah/DeepSeek-OCR-GGUF. Speed is a bandwidth ceiling (504 GB/s), not a benchmark. Methodology.

More

DeepSeek OCR on every GPU and Mac · Every model that runs on the RTX 4070 · Other models that fit 12 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (deepseek-ai/DeepSeek-OCR), NVIDIA specs. Data as of 2026-11-17.