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

Can Inkling run on the RTX 4060 Ti 16GB?

No. Even at 2-bit with 8K context, Inkling needs about 335 GB, more than the 15.2 GB usable on the RTX 4060 Ti 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.

+ 0.2 GB with image input. The figures on this page are for text only. With image input enabled, the vision projector (mmproj) file loads alongside the model. llama.cpp's -hf downloads and loads it automatically unless you add --no-mmproj. Calculator with image input on.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K)334 GB No335 GB No342 GB No366 GB No—
3-bit (Q3_K_M)435 GB No436 GB No443 GB No467 GB No—
4-bit (Q4_K_M)544 GB No545 GB No551 GB No576 GB No—
5-bit (Q5_K_M)634 GB No635 GB No641 GB No666 GB No—
6-bit (Q6_K)729 GB No730 GB No736 GB No761 GB No—
8-bit (Q8_0) •800 GB No801 GB No807 GB No832 GB No—
16-bit (F16/BF16) •1766 GB No1767 GB No1773 GB No1798 GB No—

• real GGUF file size from unsloth/inkling-GGUF. Speed is a bandwidth ceiling (288 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

Inkling on every GPU and Mac · Every model that runs on the RTX 4060 Ti 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 (thinkingmachines/Inkling), NVIDIA specs. Model data last checked 2026-11-18; refreshed hourly.