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

Can Ling 3.0 Flash Sante run on the RTX 4070 Ti?

Not fully in VRAM. Even at 2-bit with 8K context, Ling 3.0 Flash Sante needs about 47.2 GB, more than the 11.4 GB usable on the RTX 4070 Ti. It can still run with offload (slower): Q4_K_M with part of the model in system RAM, about 18–34 tokens/sec (estimate). Details and command.

Runs with offload (slower)

Runs with offload 4-bit (Q4_K_M) at 8K context: all attention layers plus the experts of 4 of 41 MoE layers on the RTX 4070 Ti (about 9.6 GB), and the experts of the other 37 layers in system RAM (about 65.6 GB). Needs a PC with at least 128 GB of system RAM. Estimated speed: 18–34 tokens/sec (usable for chat), versus a bandwidth ceiling of ~143 tok/s if it fit fully in VRAM.

llama-server -hf bartowski/Ling-3.0-flash-Sante-GGUF:Q4_K_M -c 8192 -ngl 999 --n-cpu-moe 38

Estimate, not a benchmark. The command downloads the GGUF from Hugging Face. 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) •47.0 GB No47.2 GB No48.3 GB No52.7 GB No—
3-bit (Q3_K_M) •58.2 GB No58.3 GB No59.5 GB No63.9 GB No—
4-bit (Q4_K_M) •75.8 GB No75.9 GB No77.0 GB No81.5 GB No—
5-bit (Q5_K_M) •91.8 GB No92.0 GB No93.1 GB No97.5 GB No—
6-bit (Q6_K) •105 GB No105 GB No106 GB No110 GB No—
8-bit (Q8_0) •127 GB No127 GB No128 GB No133 GB No—
16-bit (F16/BF16) •238 GB No239 GB No240 GB No244 GB No—

• real GGUF file size from bartowski/Ling-3.0-flash-Sante-GGUF. Speed is a bandwidth ceiling (504 GB/s), not a benchmark. Methodology.

Hardware that does fit it

Mac M4 Pro 64GBMac M1 Max 64GBMac M4 Max 64GBA100 80GBH100 PCIeH100 SXM

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 3.0 Flash Sante on every GPU and Mac · Every model that runs on the RTX 4070 Ti · Other models that fit 12 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-3.0-flash-Sante), NVIDIA specs. Model data last checked 2026-11-18; refreshed hourly.