Can Intern S1 run on the RTX 5060 Ti 16GB?
Not fully in VRAM. Even at 2-bit with 8K context, Intern S1 needs about 86.2 GB, more than the 15.2 GB usable on the RTX 5060 Ti 16GB. It can still run with offload (slower): Q3_K_M with part of the model in system RAM, about 3.3–6.3 tokens/sec (estimate). Details and command.
Runs with offload (slower)
Runs with offload 3-bit (Q3_K_M) at 8K context: all attention layers plus the experts of 5 of 94 MoE layers on the RTX 5060 Ti 16GB (about 13.2 GB), and the experts of the other 89 layers in system RAM (about 97.9 GB). Needs a PC with at least 128 GB of system RAM. Estimated speed: 3.3–6.3 tokens/sec (slow but usable), versus a bandwidth ceiling of ~33 tok/s if it fit fully in VRAM.
llama-server -m intern-s1-Q3_K_M.gguf -c 8192 -ngl 999 --n-cpu-moe 89
Estimate, not a benchmark. The GGUF repo we found (internlm/Intern-S1-GGUF) has no Q3_K_M file; point -m at your own Q3_K_M GGUF. 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.
+ 5.6 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
| Quant | 4K ctx | 8K ctx | 32K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|
| 2-bit (Q2_K) | 85.5 GB No | 86.2 GB No | 90.6 GB No | — |
| 3-bit (Q3_K_M) | 111 GB No | 112 GB No | 116 GB No | — |
| 4-bit (Q4_K_M) | 138 GB No | 139 GB No | 144 GB No | — |
| 5-bit (Q5_K_M) | 161 GB No | 162 GB No | 166 GB No | — |
| 6-bit (Q6_K) | 185 GB No | 186 GB No | 190 GB No | — |
| 8-bit (Q8_0) • | 234 GB No | 235 GB No | 239 GB No | — |
| 16-bit (F16/BF16) • | 439 GB No | 440 GB No | 445 GB No | — |
• real GGUF file size from internlm/Intern-S1-GGUF. Speed is a bandwidth ceiling (448 GB/s), not a benchmark. Methodology.
Hardware that does fit it
RTX PRO 6000 BlackwellDGX SparkRyzen AI Max+ 395 128GBMac M3 Max 128GBMac M4 Max 128GBH200
What fits instead
- Cheapest listed GPU that runs Intern S1: 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
Intern S1 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 (internlm/Intern-S1), NVIDIA specs. Model data last checked 2026-11-18; refreshed hourly.