Can I Run Phi-4 Mini on RTX 3090 Desktop (24 GB VRAM, 64 GB RAM)?

Written by Jakub Rusinowski · Last updated February 4, 2025

Yes — comfortably

Yes, comfortably — Phi-4 Mini (3.8B) at Q8_0 needs about 5.9 GB of the 24 GB usable on RTX 3090 Desktop (24 GB VRAM, 64 GB RAM), leaving ~18.1 GB spare and running at ~114.1 tok/s (estimated), with room for about 65,536 tokens of context.

Confidence: high · Recommended quantization: Q8_0 · Estimated speed: ~114.1 tok/s

RTX 3090 Desktop (24 GB VRAM, 64 GB RAM) — what it gives a model

Usable memory for models24 GB
Memory bandwidth936 GB/s
Form factorDesktop
Operating systemWindows or Linux
Memory upgradeableYes

Phi-4 Mini on RTX 3090 Desktop (24 GB VRAM, 64 GB RAM): memory by quantization

QuantMemory neededFits 24 GB?Max contextEst. speedDownload
F169.5 GB✓ Yes64K~72.3 tok/s7.6 GB
Q8_05.9 GB✓ Yes64K~114.1 tok/s4 GB
Q6_K5 GB✓ Yes64K~134.2 tok/s3.1 GB
Q5_K_M4.6 GB✓ Yes64K~146 tok/s2.7 GB
Q4_K_M4.2 GB✓ Yes64K~159.3 tok/s2.3 GB
Q3_K_M3.5 GB✓ Yes64K~188 tok/s1.6 GB
Q2_K3.1 GB✓ Yes64K~208.8 tok/s1.2 GB

RTX 3090 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-4 Mini on RTX 3090 Desktop (24 GB VRAM, 64 GB RAM)?

Yes, comfortably — Phi-4 Mini (3.8B) at Q8_0 needs about 5.9 GB of the 24 GB usable on RTX 3090 Desktop (24 GB VRAM, 64 GB RAM), leaving ~18.1 GB spare and running at ~114.1 tok/s (estimated), with room for about 65,536 tokens of context.

Which quantization of Phi-4 Mini should I use on RTX 3090 Desktop (24 GB VRAM, 64 GB RAM)?

Q8_0 — it needs about 5.9 GB of the 24 GB available, downloads as roughly 4 GB, and runs at an estimated 114.1 tokens/sec with up to 64K of context.

What limits Phi-4 Mini on RTX 3090 Desktop (24 GB VRAM, 64 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 3090 Desktop (24 GB VRAM, 64 GB RAM)

Phi-4 Mini on GPUs

What This Model Is Good At

Model & Tools

← Can I Run It? | Phi-4 Mini model page | Check your hardware