microsoft / image-text-to-text updated 7 months ago

Phi-3.5-vision-instruct

Name: Phi-3.5-vision-instruct
Author: microsoft

Phi-3.5-vision is a lightweight, state-of-the-art open multimodal model built upon datasets which include - synthetic data and filtered publicly available websites - with a focus on very high-quality, reasoning dense data both on text and vision. The model belongs to the Phi-3 model family, and the multimodal version comes with 128K context length (in tokens) it can support. The model underwent a rigorous enhancement...

Params

4.2 B

Context

131,072

Downloads 30d

1.3 M

Likes

738

Commercial use: allowed mit Not gated SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days

1.3 M1.2 M

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	bf16	8.3 GB	10.2 GB	✅ Runs comfortably
model.safetensors (bf16, full)	bf16 + 128K ctx	8.3 GB	19.6 GB	✅ Runs comfortably

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Architecture: Phi3VForCausalLM
Parameters: 4.2 B
Tensor type: BF16
Context length: 131,072
Vocabulary: 32,064
Layers / heads: 32 / 32
Licence: mit
First seen on the Hub: 2024-08-16
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Family

Base model and the most-downloaded derivatives in the catalog.

Derivative VLM2Vec-Full TIGER-Lab 599 K

Compare with

Qwen3.5-9B 12.4 M Qwen2.5-VL-7B-Instruct 9.3 M Qwen2.5-VL-3B-Instruct 8.2 M Qwen3.5-4B 6.7 M Qwen3-VL-4B-Instruct 4.0 M chandra-ocr-2 3.2 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB