RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Ornith 1.5 122B run on the L40S?

Yes. At 8K context the best fit is Q2_K, using about 44.7 GB of the 45.6 GB usable on the L40S. Estimated speed ceiling: ~181 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K)44.7 GB Tight44.7 GB Tight45.3 GB Tight47.6 GB No181
3-bit (Q3_K_M)57.9 GB No58.0 GB No58.6 GB No60.8 GB No—
4-bit (Q4_K_M)72.2 GB No72.3 GB No72.8 GB No75.1 GB No—
5-bit (Q5_K_M)84.0 GB No84.1 GB No84.6 GB No86.9 GB No—
6-bit (Q6_K)96.5 GB No96.6 GB No97.2 GB No99.4 GB No—
8-bit (Q8_0) •124 GB No125 GB No125 GB No127 GB No—
16-bit (F16/BF16) •233 GB No233 GB No234 GB No236 GB No—

• real GGUF file size from unsloth/Ornith-1.5-122B-GGUF. Speed is a bandwidth ceiling (864 GB/s), not a benchmark. Methodology.

More

Ornith 1.5 122B 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 (ornith-ai/Ornith-1.5-122B), NVIDIA specs. Data as of 2026-11-17.