RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Qwen3.8 2.4T A95B run on the RTX 6000 Ada?

No. Even at 2-bit with 8K context, Qwen3.8 2.4T A95B needs about 856 GB, more than the 45.6 GB usable on the RTX 6000 Ada.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K)856 GB No856 GB No858 GB No867 GB No—
3-bit (Q3_K_M)1115 GB No1115 GB No1117 GB No1126 GB No—
4-bit (Q4_K_M)1394 GB No1394 GB No1396 GB No1405 GB No—
5-bit (Q5_K_M)1624 GB No1625 GB No1627 GB No1636 GB No—
6-bit (Q6_K)1869 GB No1870 GB No1872 GB No1880 GB No—
8-bit (Q8_0) •2423 GB No2423 GB No2425 GB No2434 GB No—
16-bit (F16/BF16) •4558 GB No4559 GB No4561 GB No4569 GB No—

• real GGUF file size from unsloth/Qwen3.8-2.4T-A95B-GGUF. Speed is a bandwidth ceiling (960 GB/s), not a benchmark. Methodology.

More

Qwen3.8 2.4T A95B on every GPU and Mac · Every model that runs on the RTX 6000 Ada · Other models that fit 48 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (Qwen/Qwen3.8-2.4T-A95B), NVIDIA specs. Data as of 2026-11-17.