RunsOnMy ModelsGPUs & MacsBy VRAMBest GPUCan I run…?API pricesVRAM calculatorNew

Can Qwen3.8 2.4T A95B run on the RTX A6000?

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 A6000.

Even with llama.cpp CPU offload (-ngl, --n-cpu-moe) and 128 GB of system RAM, this model does not fit at 2-bit, or the card cannot hold a useful share of it. See the offload method.

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 (768 GB/s), not a benchmark. Methodology.

What fits instead

"Runs" and "fits" mean the whole model in GPU memory at 8K context (4-bit or better for the model pick). Prices are US launch MSRPs, not today's street prices. "Popular" means the 60 most-downloaded models we track.

More

Qwen3.8 2.4T A95B on every GPU and Mac · Every model that runs on the RTX A6000 · Other models that fit 48 GB VRAM · Try other settings in the calculator

Guides: Best GPU for local LLMs by budget · Can I run gpt-oss, Llama 70B or Qwen3? · Mac vs PC for local LLMs

Data: Hugging Face Hub (Qwen/Qwen3.8-2.4T-A95B), NVIDIA specs. Model data last checked 2026-11-17; refreshed hourly.