RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can GOT OCR2 0 run on the L40S?

Yes. At 8K context the best fit is F16, using about 2.8 GB of the 45.6 GB usable on the L40S. Estimated speed ceiling: ~603 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctxMax tok/s (est., 8K)
2-bit (Q2_K)1.3 GB Fits1.7 GB Fits3.9 GB Fits3218
3-bit (Q3_K_M)1.4 GB Fits1.8 GB Fits4.0 GB Fits2469
4-bit (Q4_K_M)1.5 GB Fits1.8 GB Fits4.1 GB Fits1974
5-bit (Q5_K_M)1.5 GB Fits1.9 GB Fits4.2 GB Fits1694
6-bit (Q6_K)1.6 GB Fits2.0 GB Fits4.2 GB Fits1472
8-bit (Q8_0)1.8 GB Fits2.1 GB Fits4.4 GB Fits1136
16-bit (F16/BF16)2.4 GB Fits2.8 GB Fits5.0 GB Fits603

• real GGUF file size. Speed is a bandwidth ceiling (864 GB/s), not a benchmark. Methodology.

More

GOT OCR2 0 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 (stepfun-ai/GOT-OCR2_0), NVIDIA specs. Data as of 2026-11-17.