Microsoft14B~9 GB VRAM at Q4_K_M

Phi-4 (14B) — VRAM, speed & local setup

Written by Jakub Rusinowski · Last updated

A powerhouse for 12GB+ VRAM GPUs. Exceptional reasoning capabilities derived from synthetic textbook quality data.

Phi-4 (14B) needs about 9 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.

Logic94
Creative80
Coding90

VRAM and speed by quantization

Quoted against NVIDIA RTX 4090 (24 GB). Includes the KV cache at 8K context, so it reads higher than the headline figure.

QuantVRAMSpeed (est.)Fit
Q2_K
2.63 bpw
7.1 GB~106 tok/sFits
Q3_K_M
3.41 bpw
8.4 GB~89 tok/sFits
Q4_K_M
4.83 bpw
10.9 GB~69 tok/sFits
Q5_K_M
5.67 bpw
12.4 GB~61 tok/sFits
Q6_K
6.56 bpw
14 GB~54 tok/sFits
Q8_0
8.50 bpw
17.4 GB~43 tok/sFits
F16
16.00 bpw
30.5 GB~4 tok/sOffload

Black marker = usable memory on the NVIDIA RTX 4090 (24 GB). Estimates from the memory-bandwidth roofline on the methodology page. Phi-4 (14B) VRAM calculator →

Get Phi-4 (14B) running

The cheapest catalogued GPU that runs Phi-4 (14B) is the Intel Arc B580 (12 GB).

Buy this hardware Intel Arc B580 12GB — 12 GB VRAM · 190 W board powerDeploy in the cloud now RTX 4090 on RunPod — from $0.34/hr · rate checked 2026-07

or compare on Vast.ai from $0.35/hr (typical low · varies)

As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.

Affiliate disclosure: Some links on this page are affiliate links — if you buy through them, LLM Configurator may earn a commission at no extra cost to you. As an Amazon Associate, LLM Configurator earns from qualifying purchases.
Intel Arc B580 12GB
12 GB VRAM · 190 W board power
2026 prices are volatile — check the current listing.

How to run Phi-4 (14B)

Install Ollama, then run:

ollama run phi4
Weights on Hugging Face: microsoft/phi-4 ↗

Download Phi-4 (14B) — GGUF Quantizations

Pick a quantization and open it in LM Studio, Ollama, or Jan, or download the raw .gguf file directly. Quant list and sizes resolved from Hugging Face.

Phi-4 (14B) — GGUF quants · bartowski/phi-4-GGUF

QuantSizeDownload (.gguf)
Q3_K_M5.97 GB (est.)phi-4-Q3_K_M.gguf
Q4_K_M8.45 GB (est.)phi-4-Q4_K_M.gguf
Q5_K_M9.92 GB (est.)phi-4-Q5_K_M.gguf
Q6_K11.48 GB (est.)phi-4-Q6_K.gguf
Q8_014.88 GB (est.)phi-4-Q8_0.gguf

Download in LM Studio: lms get bartowski/phi-4-GGUF

Want this model on your phone? You can run it on your desktop with LM Studio and chat from your iPhone or iPad over an encrypted link — see Run LM Studio Models on Your Phone (LM Link).

Specifications

Curated — A hand-written entry from before this catalogue recorded its sources. The figures are long-standing but their provenance is not on file.

Parameters
14 Billion
Context window
16,000
Architecture
Dense
Provider
Microsoft
Licence
MIT
Practical deployment
Laptop
Specified at
Q4_K_M
System RAM
16 GB
Record updated
2025-01-06
LicenceMITCommercial use permitted

Commercial use permitted. No usage restrictions beyond attribution.

Quality and use cases

Scores as published by the model’s authors or an independent evaluator — quality, not throughput, and not measured by us.

Best forreasoningmathstem

Can I run Phi-4 (14B) on my GPU?

Phi-4 (14B) — frequently asked questions

How much VRAM does Phi-4 (14B) need?

About 9 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.

Does Phi-4 (14B) run on an RTX 4090 (24 GB)?

Yes. Phi-4 (14B) needs about 9 GB at Q4_K_M, inside a 24 GB card, at an estimated 69 tokens/sec.

How do I run Phi-4 (14B) locally?

Install Ollama and run `ollama run phi4`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.