RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can DeepSeek OCR 2 run on the L40S?

Yes. At 8K context the best fit is F16, using about 6.6 GB of the 45.6 GB usable on the L40S. Estimated speed ceiling: ~417 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctxMax tok/s (est., 8K)
2-bit (Q2_K)2.1 GB Fits2.3 GB Fits1930
3-bit (Q3_K_M)2.4 GB Fits2.7 GB Fits1481
4-bit (Q4_K_M) •2.7 GB Fits2.9 GB Fits1257
5-bit (Q5_K_M)3.1 GB Fits3.4 GB Fits1016
6-bit (Q6_K)3.5 GB Fits3.7 GB Fits882
8-bit (Q8_0) •3.8 GB Fits4.0 GB Fits784
16-bit (F16/BF16) •6.4 GB Fits6.6 GB Fits417

• real GGUF file size from sabafallah/DeepSeek-OCR-2-GGUF. Speed is a bandwidth ceiling (864 GB/s), not a benchmark. Methodology.

More

DeepSeek OCR 2 on every GPU and Mac · Every model that runs on the L40S · Other models that fit 48 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (deepseek-ai/DeepSeek-OCR-2), NVIDIA specs. Data as of 2026-11-17.