Can Hy3 Preview run on the RTX 5060 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 5060 Ti 16GB. It can still run with offload (slower): Q2_K with part of the model in system RAM, about 5.2–10 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 5060 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: 5.2–10 tokens/sec (slow but usable), versus a bandwidth ceiling of ~57 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
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) | 106 GB No | 107 GB No | 115 GB No | 145 GB No | — |
| 3-bit (Q3_K_M) | 138 GB No | 139 GB No | 147 GB No | 177 GB No | — |
| 4-bit (Q4_K_M) | 172 GB No | 173 GB No | 181 GB No | 211 GB No | — |
| 5-bit (Q5_K_M) | 200 GB No | 201 GB No | 209 GB No | 239 GB No | — |
| 6-bit (Q6_K) | 230 GB No | 231 GB No | 239 GB No | 269 GB No | — |
| 8-bit (Q8_0) | 298 GB No | 299 GB No | 306 GB No | 336 GB No | — |
| 16-bit (F16/BF16) | 558 GB No | 560 GB No | 567 GB No | 597 GB No | — |
• real GGUF file size. Speed is a bandwidth ceiling (448 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
- Cheapest listed GPU that runs Hy3 Preview: DGX Spark (128 GB, launch MSRP $3,999) at Q2_K, fully in VRAM at 8K context.
- Largest popular model that fits the RTX 5060 Ti 16GB: gpt-oss 20B (21B, MoE) at Q8_0, about 12.3 GB at 8K context.
"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 5060 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.