Can I Run Phi 3.5 Family on RTX 3060 12 GB Desktop (12 GB VRAM, 32 GB RAM)?

Superseded model. Phi 3.5 Family has been superseded by Phi-4 Family. This page is kept for reference; the newer family is a better starting point. View Phi-4 Family →

Written by Jakub Rusinowski · Last updated August 20, 2024

Yes — comfortably

Yes, comfortably — Phi 3.5 Mini at Q8_0 needs about 5.6 GB of the 12 GB usable on RTX 3060 12 GB Desktop (12 GB VRAM, 32 GB RAM), leaving ~6.4 GB spare and running at ~53.5 tok/s (estimated), with room for about 65,536 tokens of context.

Confidence: high · Recommended quantization: Q8_0 · Estimated speed: ~53.5 tok/s

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

Usable memory for models12 GB
Memory bandwidth360 GB/s
Form factorDesktop
Operating systemWindows or Linux
Memory upgradeableYes

Phi 3.5 Family on RTX 3060 12 GB Desktop (12 GB VRAM, 32 GB RAM): memory by quantization

QuantMemory neededFits 12 GB?Max contextEst. speedDownload
F169.2 GB✓ Yes32K~31.4 tok/s7.6 GB
Q8_05.6 GB✓ Yes64K~53.5 tok/s4 GB
Q6_K4.7 GB✓ Yes64K~65.5 tok/s3.1 GB
Q5_K_M4.3 GB✓ Yes64K~72.9 tok/s2.7 GB
Q4_K_M3.9 GB✓ Yes64K~81.7 tok/s2.3 GB
Q3_K_M3.2 GB✓ Yes64K~102.7 tok/s1.6 GB
Q2_K2.9 GB✓ Yes64K~119.6 tok/s1.2 GB

RTX 3060 12 GB desktop limitations

Recommended setup

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

How these numbers are calculated

FAQ

Can I run Phi 3.5 Family on RTX 3060 12 GB Desktop (12 GB VRAM, 32 GB RAM)?

Yes, comfortably — Phi 3.5 Mini at Q8_0 needs about 5.6 GB of the 12 GB usable on RTX 3060 12 GB Desktop (12 GB VRAM, 32 GB RAM), leaving ~6.4 GB spare and running at ~53.5 tok/s (estimated), with room for about 65,536 tokens of context.

Which quantization of Phi 3.5 Family should I use on RTX 3060 12 GB Desktop (12 GB VRAM, 32 GB RAM)?

Q8_0 — it needs about 5.6 GB of the 12 GB available, downloads as roughly 4 GB, and runs at an estimated 53.5 tokens/sec with up to 64K of context.

What limits Phi 3.5 Family on RTX 3060 12 GB Desktop (12 GB VRAM, 32 GB RAM)?

Nothing binding — the model fits with headroom and generates at a usable speed on this hardware.

Which runtime should I use?

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

Other Computers

Other Models on RTX 3060 12 GB Desktop (12 GB VRAM, 32 GB RAM)

Phi 3.5 Family on GPUs

What This Model Is Good At

Model & Tools

← Can I Run It? | Phi 3.5 Family model page | Check your hardware