RunLocalAI
phi
14B parameters
Commercial OK
Multimodal

Phi-4 Multimodal

Multimodal variant of Phi-4 14B. Vision + text. Smaller than Llama 4 Scout but covers most image-Q&A workflows; right-sized for 16GB consumer cards.

License: MIT·Released Feb 25, 2026·Context: 131,072 tokens

Overview

Multimodal variant of Phi-4 14B. Vision + text. Smaller than Llama 4 Scout but covers most image-Q&A workflows; right-sized for 16GB consumer cards.

Family & lineage

How this model relates to others in its lineage. Family members share architecture and training-data roots; parent / children edges record direct distillation or fine-tune relationships.

Parent / base model
Phi-4 14B14B
Consumer
Family siblings (phi-4)
Phi-4 Mini 4B3.8B
Edge
Phi-4 Reasoning Mini 4B3.8B
Edge
Phi-4 Multimodal14B
You are here
Phi-4 Reasoning 14B14B
Consumer
Phi-4 14B14B
Consumer

Strengths

  • Multimodal at consumer-card scale
  • MIT

Weaknesses

  • Vision quality below frontier multimodal models

Quantization variants

Each quantization trades model quality for file size and VRAM. Q4_K_M is the most popular starting point.

QuantizationFile sizeVRAM required
Q4_K_M9.0 GB12 GB

Get the model

HuggingFace

Original weights

huggingface.co/microsoft/Phi-4-multimodal

Source repository — direct quantization required.

Hardware that runs this

Cards with enough VRAM for at least one quantization of Phi-4 Multimodal.

NVIDIA GB200 NVL72
13824GB · nvidia
AMD Instinct MI355X
288GB · amd
AMD Instinct MI325X
256GB · amd
AMD Instinct MI300X
192GB · amd
NVIDIA B200
192GB · nvidia
NVIDIA H100 NVL
188GB · nvidia
NVIDIA H200
141GB · nvidia
Intel Gaudi 3
128GB · intel
Compare alternatives

Models worth comparing

Same parameter band, plus what's one tier above and below — so you can decide what actually fits your hardware.

Step down
Smaller — faster, runs on weaker hardware

Frequently asked

What's the minimum VRAM to run Phi-4 Multimodal?

12GB of VRAM is enough to run Phi-4 Multimodal at the Q4_K_M quantization (file size 9.0 GB). Higher-quality quantizations need more.

Can I use Phi-4 Multimodal commercially?

Yes — Phi-4 Multimodal ships under the MIT, which permits commercial use. Always read the license text before deployment.

What's the context length of Phi-4 Multimodal?

Phi-4 Multimodal supports a context window of 131,072 tokens (about 131K).

Does Phi-4 Multimodal support images?

Yes — Phi-4 Multimodal is multimodal and accepts text + vision inputs. Vision support requires a runner that handles its image-conditioning architecture.

Source: huggingface.co/microsoft/Phi-4-multimodal

Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify model claims.