Can I Run Qwen 2.5 Family on RTX 3060 12 GB Desktop (12 GB VRAM, 32 GB RAM)?

Superseded model. Qwen 2.5 Family has been superseded by Qwen 3. This page is kept for reference; the newer family is a better starting point. View Qwen 3 →

Written by Jakub Rusinowski · Last updated November 12, 2024

Yes, but it is tight

Yes, but it is tight — Qwen 2.5 14B Instruct at Q4_K_M needs about 10.9 GB of the 12 GB usable on RTX 3060 12 GB Desktop (12 GB VRAM, 32 GB RAM), leaving only ~1.1 GB before the runtime starts swapping. Expect ~27.4 tok/s (estimated), with room for about 8,192 tokens of context.

Confidence: medium · Recommended quantization: Q4_K_M · Estimated speed: ~27.4 tok/s

RTX 3060 12 GB Desktop (12 GB VRAM, 32 GB RAM) — what it gives a model

Usable memory for models	12 GB
Memory bandwidth	360 GB/s
Form factor	Desktop
Operating system	Windows or Linux
Memory upgradeable	Yes

Qwen 2.5 Family on RTX 3060 12 GB Desktop (12 GB VRAM, 32 GB RAM): memory by quantization

Quant	Memory needed	Fits 12 GB?	Max context	Est. speed	Download
F16	30.4 GB	✗ No	—	—	28 GB
Q8_0	17.3 GB	✗ No	—	—	14.9 GB
Q6_K	13.9 GB	✗ No	—	—	11.5 GB
Q5_K_M	12.3 GB	✗ No	—	—	9.9 GB
Q4_K_M	10.9 GB	✓ Yes	8K	~27.4 tok/s	8.5 GB
Q3_K_M	8.4 GB	✓ Yes	16K	~36.6 tok/s	6 GB
Q2_K	7 GB	✓ Yes	32K	~44.9 tok/s	4.6 GB

Which Qwen 2.5 Family sizes fit

Variant	Needs at Q4_K_M	Fits?	Est. speed
Qwen 2.5 72B Instruct	47 GB	✗ Too large	—
Qwen 2.5 Coder 32B	22.3 GB	✗ Too large	—
Qwen 2.5 14B Instruct	10.9 GB	✓ Fits	~27.4 tok/s
Qwen 2.5 7B Instruct	5.9 GB	✓ Fits	~49.7 tok/s

What to watch out for

Only ~1.1 GB of headroom at Q4_K_M: a longer context or a second application can push this into swapping.
2 larger variants of Qwen 2.5 Family do not fit and would need CPU offload or different hardware.

RTX 3060 12 GB desktop limitations

The budget entry point to local AI: 12 GB runs 7–14B models well and nothing larger without offload.

Recommended setup

Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving

How these numbers are calculated

Memory need = quantized weights + KV cache at 8,192 tokens (f16) + 0.8 GB runtime overhead.
12 GB of VRAM on the NVIDIA GeForce RTX 3060 (12GB) at 360 GB/s.
32 GB of system RAM available for CPU offload when a model exceeds VRAM.
Throughput is a memory-bandwidth roofline estimate, not a measurement. It is labelled "estimated" everywhere it appears.
KV cache is computed from this model's published attention configuration.

FAQ