RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Ling 3.0 flash run on the L40S?

Yes. At 8K context the best fit is Q2_K, using about 43.8 GB of the 45.6 GB usable on the L40S. Estimated speed ceiling: ~428 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •43.6 GB Tight43.8 GB Tight44.9 GB Tight49.4 GB No428
3-bit (Q3_K_M) •55.8 GB No56.0 GB No57.1 GB No61.5 GB No—
4-bit (Q4_K_M) •73.3 GB No73.5 GB No74.6 GB No79.1 GB No—
5-bit (Q5_K_M) •85.3 GB No85.5 GB No86.6 GB No91.0 GB No—
6-bit (Q6_K) •103 GB No103 GB No104 GB No108 GB No—
8-bit (Q8_0) •127 GB No127 GB No128 GB No133 GB No—
16-bit (F16/BF16) •238 GB No239 GB No240 GB No244 GB No—

• real GGUF file size from bartowski/Ling-3.0-flash-GGUF. Speed is a bandwidth ceiling (864 GB/s), not a benchmark. Methodology.

More

Ling 3.0 flash 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 (inclusionAI/Ling-3.0-flash), NVIDIA specs. Data as of 2026-11-17.