Can KORMo Web 11B run on the RTX 3060 Ti?
Yes. At 8K context the best fit is Q2_K, using about 5.8 GB of the 7.6 GB usable on the RTX 3060 Ti. Estimated speed ceiling: ~107 tokens/sec.
Better quality with offload: 4-bit (Q4_K_M)
Runs with offload 4-bit (Q4_K_M) at 8K context: 33 of 40 layers on the RTX 3060 Ti (about 6.9 GB) and the other 7 in system RAM (about 1.3 GB). Needs a PC with at least 32 GB of system RAM. Estimated speed: 14–23 tokens/sec (usable for chat), versus a bandwidth ceiling of ~65 tok/s if it fit fully in VRAM.
llama-server -m kormo-web-11b-Q4_K_M.gguf -c 8192 -ngl 33
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, lower -ngl by 2-3; if VRAM is left over, raise 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) | 5.2 GB Fits | 5.8 GB Fits | 9.5 GB No | 24.5 GB No | 107 |
| 3-bit (Q3_K_M) | 6.4 GB Fits | 7.0 GB Tight | 10.7 GB No | 25.7 GB No | 82 |
| 4-bit (Q4_K_M) | 7.6 GB No | 8.3 GB No | 12.0 GB No | 27.0 GB No | — |
| 5-bit (Q5_K_M) | 8.7 GB No | 9.3 GB No | 13.1 GB No | 28.1 GB No | — |
| 6-bit (Q6_K) | 9.8 GB No | 10.4 GB No | 14.2 GB No | 29.2 GB No | — |
| 8-bit (Q8_0) | 12.3 GB No | 13.0 GB No | 16.7 GB No | 31.7 GB No | — |
| 16-bit (F16/BF16) | 22.1 GB No | 22.7 GB No | 26.5 GB No | 41.5 GB No | — |
• real GGUF file size. Speed is a bandwidth ceiling (448 GB/s), not a benchmark. Methodology.
What fits instead
- Cheapest listed GPU that runs KORMo Web 11B: Arc B580 (12 GB, launch MSRP $249) at Q5_K_M, fully in VRAM at 8K context.
- Largest popular model that fits the RTX 3060 Ti: Qwen3.5 9B (9.7B) at Q4_K_M, about 6.4 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
KORMo Web 11B on every GPU and Mac · Every model that runs on the RTX 3060 Ti · Other models that fit 8 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 (KORMo-VL/KORMo-Web-11B), NVIDIA specs. Model data last checked 2026-11-17; refreshed hourly.