Microsoft/Dense

Phi-4-multimodal 14B

Name: Phi-4-multimodal 14B
Author: Microsoft

Phi-4 Multimodal — understands images, audio, and text in one model.

chatvisionreasoningThinkingTool Use

5.57B

Parameters

128K

Context length

Benchmarks

Quantizations

Architecture

Dense

Released

2025-01-07

Layers

KV Heads

Head Dim

128

Family

phi

Quantization Options

Context length:

Quant	Bits	VRAM @ 16K	Quality
Q3_K_M	4	4.8 GB 3.3 + 1.5 KV	low
Q3_K_L	4.3	5.0 GB 3.5 + 1.5 KV	moderate
IQ4_XS	4.46	5.1 GB 3.6 + 1.5 KV	moderate
Q4_K_S	4.67	5.2 GB 3.7 + 1.5 KV	moderate
Q4_K_M	4.89	5.4 GB 3.9 + 1.5 KV	good
Q5_K_S	5.57	5.9 GB 4.4 + 1.5 KV	good
Q5_K_M	5.7	6.0 GB 4.5 + 1.5 KV	good
Q6_K	6.56	6.6 GB 5.1 + 1.5 KV	excellent
Q8_0	8.5	7.9 GB 6.4 + 1.5 KV	lossless
FP16	16	13.1 GB 11.6 + 1.5 KV	lossless

Select your GPU above to see speed estimates and compatibility for each quantization.

Deploying for a team or in production? Size GPUs, cost & scaling in Enterprise →

▸ READY TO RUN THIS?RENT BY THE HOUR

RENT A GPU AND RUN PHI-4-MULTIMODAL 14B NOW

Rent on Vast.ai →Or RunPod →

Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.

Community Ratings

Loading ratings...

Benchmarks (10)

Arena Elo1465

MMBench86.7

IFEval64.2

MMMU55.1

BBH49.4

MMLU-PRO40.8

BigCodeBench37.6

MATH19.6

MUSR13.1

GPQA11.5

Run this model

▸Easiest way to get started·Beginners

DOCS ↗

curl -fsSL https://ollama.com/install.sh | sh

$ollama run phi4:14b-q4_K_M

Downloads and runs automatically. Add --verbose for speed stats.

▸ SETUP GUIDE

Auto-setup with fitmyllm CLI

Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.

pip install fitmyllmthen run fitmyllmLearn more

Auto-detect GPULive tok/s in chatSpeed benchmarks9 inference engines

HuggingFace Ollama Library GGUF Downloads Build Hardware

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

NVIDIA Tesla C1080

4 GB VRAM • 102 GB/s

NVIDIA

NVIDIA Tesla K10

4 GB VRAM • 160 GB/s

NVIDIA

NVIDIA Tesla M4

4 GB VRAM • 88 GB/s

NVIDIA

NVIDIA GeForce GTX 1050 Ti

4 GB VRAM • 112 GB/s

NVIDIA

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

AMD Radeon Instinct MI8

4 GB VRAM • 512 GB/s

AMD

NVIDIA GeForce GTX 1650

4 GB VRAM • 128 GB/s

NVIDIA

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA GeForce GTX 1650 SUPER

4 GB VRAM • 192 GB/s

NVIDIA

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

AMD Radeon RX 5300 XT OEM

4 GB VRAM • 112 GB/s

AMD

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

AMD Radeon RX 5500 OEM

4 GB VRAM • 224 GB/s

AMD

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

AMD Radeon RX 5500 XT

4 GB VRAM • 224 GB/s

AMD

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

AMD Radeon RX 5500M

4 GB VRAM • 224 GB/s

AMD

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA GeForce GTX 1650 GDDR6

4 GB VRAM • 192 GB/s

NVIDIA

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA GeForce GTX 1650 TU106

4 GB VRAM • 192 GB/s

NVIDIA

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA GeForce GTX 1650 TU116

4 GB VRAM • 192 GB/s

NVIDIA

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA GeForce GTX 1630

4 GB VRAM • 96 GB/s

NVIDIA

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA GeForce RTX 3050 4 GB

4 GB VRAM • 192 GB/s

NVIDIA

$149

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA RTX A1000 Embedded

4 GB VRAM • 224 GB/s

NVIDIA

NVIDIA RTX A2000 Embedded

4 GB VRAM • 192 GB/s

NVIDIA

AMD Radeon RX 6400

4 GB VRAM • 128 GB/s

AMD

$139

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

AMD Radeon RX 6500 XT

4 GB VRAM • 144 GB/s

AMD

$70

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

AMD Radeon RX 6500M

4 GB VRAM • 144 GB/s

AMD

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

AMD Radeon RX 6600S

4 GB VRAM • 224 GB/s

AMD

$175

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

Intel Arc A310

4 GB VRAM • 124 GB/s

INTEL

$79

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

Intel Arc A350

4 GB VRAM • 124 GB/s

INTEL

$99

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

Intel Arc A350M

4 GB VRAM • 112 GB/s

INTEL

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

Intel Arc A370M

4 GB VRAM • 112 GB/s

INTEL

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

AMD Radeon RX 6450M

4 GB VRAM • 128 GB/s

AMD

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

AMD Radeon RX 6550M

4 GB VRAM • 144 GB/s

AMD

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

AMD Radeon RX 6550S

4 GB VRAM • 128 GB/s

AMD

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

NVIDIA GeForce RTX 4010

4 GB VRAM • 96 GB/s

NVIDIA

$199

Amazon Newegg eBay PCPartPicker Rent on RunPod Rent on Vast.ai

Find the best GPU for Phi-4-multimodal 14B

Build Hardware for Phi-4-multimodal 14B

Model Card

View on HuggingFace

Phi-4 Multimodal — understands images, audio, and text in one model.

QUANT	BPW	VRAM	QUALITY
Q3_K_M	4	3.3 GB	88%
Q3_K_L	4.3	3.5 GB	90%
IQ4_XS	4.46	3.6 GB	92%
Q4_K_S	4.67	3.7 GB	93%
Q4_K_M	4.89	3.9 GB	94%
Q5_K_S	5.57	4.4 GB	96%
Q5_K_M	5.7	4.5 GB	96%
Q6_K	6.56	5.1 GB	97%
Q8_0	8.5	6.4 GB	100%
FP16	16	11.6 GB	100%

Phi-4-multimodal 14B

Quantization Options

Community Ratings

Benchmarks (10)

Run this model

Auto-setup with fitmyllm CLI

GPUs that can run this model

Model Card

Phi-4-multimodal 14B — 5.57B Dense.