LIVETracking 971 AI models from 268 providers.
Beta
Home/Models/Phi 3.5 Vision Instruct
Microsoft logo

Phi 3.5 Vision Instruct

by Microsoft · Released Aug 2024

Open Source
Compare
Context
N/A
Input $/1M
TBD
Output $/1M
TBD
Type
image-text-to-text
License
Open Source
Benchmarks
0 tested
Data updated today
About

Microsoft image text to text model. 1200K downloads on HuggingFace.

No benchmark data available yet.

Model Family · Microsoft Phi 3
Apr 2024
27.6
N/AN/Actx7 benchmarks
Aug 2024
28.2+0.6
N/AN/Actx6 benchmarks
Aug 2024
N/AN/Actx
Jan 2024
58.6+58.6
N/AN/Actx10 benchmarks
Jan 2024
61.0+2.4
N/AN/Actx8 benchmarks
Jan 2024
67.4+6.4
N/AN/Actx8 benchmarks
See the full Phi 3 family →
Similar Models
Alibaba Qwen logo
Qwen VL Max
Alibaba Qwen
0.0$0.52/1M
openrouter logo
Elephant
openrouter
0.0Free
arcee-ai logo
Trinity Large Thinking
arcee-ai
0.0$0.22/1M
Links
Info
Microsoft
Research
Technical Report
Documentation
API DocsPlayground
Community
@Microsoft
Source Code
GitHubHugging Face
BenchGecko API
microsoft-phi-35-vision-instruct
Specifications
  • Typeimage-text-to-text
  • ContextN/A
  • ReleasedAug 2024
  • LicenseOpen Source
  • StatusActive
Available On
Microsoft logoMicrosoftTBD
Learn More
transformeropen-weightstokens
Share & Export
Tweet
Related Models
Alibaba Qwen logoQwen VL Max
0.0
openrouter logoElephant
0.0
arcee-ai logoTrinity Large Thinking
0.0
OpenAI logoGPT-4o Audio
0.0
Phi 3.5 Vision Instruct is an open-source image-text-to-text AI model by Microsoft, released in August 2024.

Related Models

Qwen VL Max · Alibaba QwenElephant · openrouterTrinity Large Thinking · arcee-aiGPT-4o Audio · OpenAIGemma 4 26B A4B (free) · Google DeepMind

Benchmarks

Related Pages

Microsoft · ProviderAll ModelsCompare Models