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

Can Ling 1T run on the Arc A770 16GB?

No. Even at 2-bit with 8K context, Ling 1T needs about 329 GB, more than the 15.2 GB usable on the Arc A770 16GB.

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 ctxMax tok/s (est., 8K)
2-bit (Q2_K) •328 GB No329 GB No337 GB No—
3-bit (Q3_K_M) •427 GB No428 GB No436 GB No—
4-bit (Q4_K_M) •569 GB No570 GB No577 GB No—
5-bit (Q5_K_M)665 GB No667 GB No674 GB No—
6-bit (Q6_K) •768 GB No769 GB No776 GB No—
8-bit (Q8_0) •992 GB No993 GB No1000 GB No—
16-bit (F16/BF16)1864 GB No1865 GB No1873 GB No—

• real GGUF file size from bartowski/inclusionAI_Ling-1T-GGUF. Speed is a bandwidth ceiling (560 GB/s), not a benchmark. Methodology.

Hardware that does fit it

Mac M3 Ultra 512GB

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

Ling 1T on every GPU and Mac · Every model that runs on the Arc A770 16GB · Other models that fit 16 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 (inclusionAI/Ling-1T), Intel specs. Model data last checked 2026-11-18; refreshed hourly.