Model
Model explorer

Phi-4-multimodal-instruct

OPEN
Microsoft · Phi-4 family · released Feb 26, 2025

Unified text + vision + speech model (5.6B, 128K ctx) built on frozen Phi-4-mini weights with LoRA adapters.

ReasoningCodingVisionFunction callingTool useAgentic
842.4
Elo · unrated
Parameters
5.6B
Active params
5.6B (dense)
Context
128K tokens
Architecture
Unified dense Transformer (frozen Phi-4-mini backbone + modality-specific LoRA adapters for vision/speech)
License
MIT
Languages
23+
API price (in/out)
$0.08 / $0.32
Modalities
text · vision · audio
Benchmark results
Bar shows position within the tracked field; marker = field best
AI2DVision82.3%#32
best: Molmo 72B · 96.3%
ChartQAVision81.4%#31
best: MiniMax-VL-01 · 91.7%
DocVQAVision93.2%#22
best: Qwen2-VL-72B · 96.5%
MathVistaVision62.4%#41
best: Seed 2.1 Pro · 90.7%
MMBench (English)Vision86.7%#12
best: Qwen3.5-397B-A17B · 93.7%
MMMU-ProVision38.5%#49
best: Claude Opus 4.7 · 85.5%
MMMUVision55.1%#86
best: Claude Fable 5 · 89.3%
OCRBenchVision84#21
best: InternVL3-78B · 906
TextVQAVision75.6%#18
best: Molmo 2 8B · 85.7%
Video-MMEVision55.0%#23
best: Seed 2.1 Pro · 89.2%
Run it locally
VRAM @ Q4
5 GB
VRAM @ FP16
12 GB
Fits on (Q4)
RTX 3060 12GBRTX 4070 Ti 16GBRTX 3090 24GBRTX 4090 24GBRTX 5090 32GBM4 Pro 48GBM3 Max 128GBM3 Ultra 512GBA100 80GBH100 80GBH200 141GBB200 192GB
Throughput data unavailable.
Quantizations
GGUF Q4 · ONNX INT4
Phi-4 family
Elo progression across releases
Phi-4 (14B)Dec 20241016.7Phi-4-mini (3.8B)Feb 2025529.8Phi-4-mini-instructFeb 2025523.2Phi-4-multimodal (5.6B)Feb 2025842.4Phi-4-multimodal-instructFeb 2025842.4Phi-4-reasoningApr 20251292.1Phi-4-reasoning (14B)Apr 20251292.1
Resources
HFmicrosoft/Phi-4-multimodal-instructGHmicrosoft/PhiCookBookDOCStechcommunity.microsoft.com/blog/educatordeveloperblog/welcome-to-the-new-phi-4-models---microsoft-phi-4-mini--phi-4-multimodal/4386037APIAvailable via Microsoft API
API price $0.08/$0.32 · each benchmark row carries its own source badge (see methodology)