← Can It Run? — GPU compatibility matrix · Local LLMs guide
Phi-4 14B needs 8.5 GB VRAM at Q4. The RTX 3090 24GB has 24 GB.
Φ Phi-4 14B (Microsoft) is a 14B-parameter model for reasoning, math, structured tasks. Microsoft’s reasoning-focused model, punches above its size. The question is whether the RTX 3090 24GB’s 24 GB of VRAM can hold it — here’s the exact math.
VRAM requirements
| Quantization | VRAM needed | RTX 3090 24GB |
|---|---|---|
| Q4_K_M (recommended) | 8.5 GB | ✅ |
| Q8_0 (near-lossless) | 15 GB | ✅ |
Expected performance
Running Phi-4 14B at Q4 on the RTX 3090 24GB, expect roughly ~38 tokens/sec in Ollama or llama.cpp — comfortably faster than reading speed, so chat feels responsive.
Headroom: 8.5 GB used of 24 GB leaves about 15.5 GB free for KV cache (context). That’s fine for 4-8K context; for 32K+ you may need a smaller batch or a lower quant.
About the RTX 3090 24GB
Architecture: Ampere · VRAM: 24 GB · Price: ~$800 used.
Good: 24GB sweet spot for 27-34B models — best used value for LLMs
Watch out: Power hungry (350W), large, runs hot
Check current RTX 3090 24GB price on Amazon →
Related checks
Other models on the RTX 3090 24GB
🎯 LLM Hardware Checker
Enter your exact GPU + RAM, see every model you can run.
💾 VRAM Requirements
Exact VRAM per model at Q4/Q5/Q8/FP16 with context scaling.
Frequently asked questions
Can the RTX 3090 24GB run Phi-4 14B?
Yes — runs at Q4 and full Q8 quality. Phi-4 14B needs 8.5 GB VRAM at Q4_K_M; the RTX 3090 24GB has 24 GB.
How much VRAM does Phi-4 14B need?
Phi-4 14B needs about 8.5 GB at Q4_K_M (recommended) and 15 GB at Q8_0.
How many tokens per second will the RTX 3090 24GB get on Phi-4 14B?
Roughly ~38 tokens/sec at Q4 in Ollama or llama.cpp.