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

Can Hy3 Preview run on the RTX 4060 Ti 16GB?

Not fully in VRAM. Even at 2-bit with 8K context, Hy3 Preview needs about 107 GB, more than the 15.2 GB usable on the RTX 4060 Ti 16GB. It can still run with offload (slower): Q2_K with part of the model in system RAM, about 5.0–9.5 tokens/sec (estimate). Details and command.

Runs with offload (slower)

Runs with offload 2-bit (Q2_K) at 8K context: all attention layers plus the experts of 6 of 80 MoE layers on the RTX 4060 Ti 16GB (about 13.2 GB), and the experts of the other 74 layers in system RAM (about 93.7 GB). Needs a PC with at least 128 GB of system RAM. Estimated speed: 5.0–9.5 tokens/sec (slow but usable), versus a bandwidth ceiling of ~37 tok/s if it fit fully in VRAM.

llama-server -m hy3-preview-Q2_K.gguf -c 8192 -ngl 999 --n-cpu-moe 74

Estimate, not a benchmark. No GGUF repo was found on Hugging Face yet; point -m at your own GGUF file. The speed range spans dual-channel DDR4-3200 to DDR5-6000 system RAM; your CPU, RAM speed and llama.cpp version move it. If llama.cpp runs out of GPU memory, raise --n-cpu-moe by 1-2; if VRAM is left over, lower it for more speed. Recent llama.cpp builds can also pick the split automatically. How we estimate offload.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K)106 GB No107 GB No115 GB No145 GB No—
3-bit (Q3_K_M)138 GB No139 GB No147 GB No177 GB No—
4-bit (Q4_K_M)172 GB No173 GB No181 GB No211 GB No—
5-bit (Q5_K_M)200 GB No201 GB No209 GB No239 GB No—
6-bit (Q6_K)230 GB No231 GB No239 GB No269 GB No—
8-bit (Q8_0)298 GB No299 GB No306 GB No336 GB No—
16-bit (F16/BF16)558 GB No560 GB No567 GB No597 GB No—

• real GGUF file size. Speed is a bandwidth ceiling (288 GB/s), not a benchmark. Methodology.

Hardware that does fit it

DGX SparkRyzen AI Max+ 395 128GBH200Mac M2 Ultra 192GBMac M3 Ultra 256GBMac 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

Hy3 Preview 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 (tencent/Hy3-preview), NVIDIA specs. Model data last checked 2026-11-18; refreshed hourly.