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

Can Qwen3.5 27B run on the RTX 5060 Ti 16GB?

Yes. At 8K context the best fit is Q2_K, using about 12.6 GB of the 15.2 GB usable on the RTX 5060 Ti 16GB. Estimated speed ceiling: ~37 tokens/sec.

Better quality with offload: 4-bit (Q4_K_M)

Runs with offload 4-bit (Q4_K_M) at 8K context: 51 of 64 layers on the RTX 5060 Ti 16GB (about 14.6 GB) and the other 13 in system RAM (about 3.5 GB). Needs a PC with at least 32 GB of system RAM. Estimated speed: 4.9–8.2 tokens/sec (slow but usable), versus a bandwidth ceiling of ~25 tok/s if it fit fully in VRAM.

llama-server -hf bartowski/Qwen_Qwen3.5-27B-GGUF:Q4_K_M -c 8192 -ngl 51 --no-mmproj

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, 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.

+ 0.9 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: Q2_K at 8K context then needs about 13.5 GB (still fits). llama.cpp's -hf downloads and loads it automatically unless you add --no-mmproj. Calculator with image input on.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •12.3 GB Fits12.6 GB Fits14.1 GB Tight20.1 GB No37
3-bit (Q3_K_M) •14.9 GB Tight15.2 GB Tight16.7 GB No22.7 GB No30
4-bit (Q4_K_M) •17.9 GB No18.1 GB No19.6 GB No25.6 GB No—
5-bit (Q5_K_M) •20.6 GB No20.9 GB No22.4 GB No28.4 GB No—
6-bit (Q6_K) •23.2 GB No23.4 GB No24.9 GB No30.9 GB No—
8-bit (Q8_0) •28.2 GB No28.5 GB No30.0 GB No36.0 GB No—
16-bit (F16/BF16) •52.0 GB No52.3 GB No53.8 GB No59.8 GB No—

• real GGUF file size from bartowski/Qwen_Qwen3.5-27B-GGUF. Speed is a bandwidth ceiling (448 GB/s), not a benchmark. Methodology.

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

Qwen3.5 27B 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 (Qwen/Qwen3.5-27B), NVIDIA specs. Model data last checked 2026-11-18; refreshed hourly.