RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Hy Memory 30B A3B run on the L40S?

Yes. At 8K context the best fit is Q8_0, using about 31.1 GB of the 45.6 GB usable on the L40S. Estimated speed ceiling: ~271 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K)11.5 GB Fits11.9 GB Fits14.1 GB Fits23.1 GB Fits768
3-bit (Q3_K_M)14.7 GB Fits15.1 GB Fits17.3 GB Fits26.3 GB Fits589
4-bit (Q4_K_M)18.1 GB Fits18.5 GB Fits20.7 GB Fits29.7 GB Fits471
5-bit (Q5_K_M)21.0 GB Fits21.3 GB Fits23.6 GB Fits32.6 GB Fits404
6-bit (Q6_K)24.0 GB Fits24.3 GB Fits26.6 GB Fits35.6 GB Fits351
8-bit (Q8_0)30.8 GB Fits31.1 GB Fits33.4 GB Fits42.4 GB Tight271
16-bit (F16/BF16)57.0 GB No57.4 GB No59.6 GB No68.6 GB No—

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

More

Hy Memory 30B A3B 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 (tencent/Hy-Memory-30B-A3B), NVIDIA specs. Data as of 2026-11-17.