IBM/Dense

IBMGranite 4.0 3B Vision

granite-vision-3.2-2b is a compact and efficient vision-language model, specifically designed for visual document understanding, enabling automated content extraction from tables, charts, infographics, plots, diagrams, and more.

chatvisionmultilingual
3B
Parameters
128K
Context length
7
Benchmarks
6
Quantizations
0
Architecture
Dense
Released
2025-12-01
Layers
40
KV Heads
8
Head Dim
64
Family
granite

Quantization Options

QuantBitsVRAMQuality
Q4_K_M4.892.3 GBgood
Q5_K_S5.572.6 GBgood
Q5_K_M5.72.6 GBgood
Q6_K6.562.9 GBexcellent
Q8_08.53.7 GBlossless
FP16166.5 GBlossless

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

READY TO RUN THIS?RENT BY THE HOUR

RENT A GPU AND RUN GRANITE 4.0 3B VISION NOW

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

Community Ratings

Loading ratings...

Benchmarks (7)

IFEval62.9
MMMU37.0
BBH21.8
MMLU-PRO20.2
MATH15.3
GPQA5.3
MUSR4.9

Run this model

Easiest way to get started·Beginners
DOCS ↗
curl -fsSL https://ollama.com/install.sh | sh
$ollama run granite:3b-q4_K_M

Tag may need adjustment — check ollama.com/library/granite for available tags.

▸ 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

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

NVIDIA Tesla C2050
3 GB VRAM • 144 GB/s
NVIDIA
NVIDIA Tesla M2050
3 GB VRAM • 148 GB/s
NVIDIA
NVIDIA Tesla S2050
3 GB VRAM • 148 GB/s
NVIDIA

Find the best GPU for Granite 4.0 3B Vision

Build Hardware for Granite 4.0 3B Vision
▸ SPEC SHEET

Granite 4.0 3B Vision3B Dense.

▸ SPECIFICATIONS
PARAMETERS
3B
ARCHITECTURE
Dense Transformer
CONTEXT LENGTH
128K tokens
CAPABILITIES
chat, vision, multilingual
RELEASE DATE
2025-12-01
PROVIDER
IBM
FAMILY
granite
▸ VRAM REQUIREMENTS
QUANTBPWVRAMQUALITY
Q4_K_M4.892.3 GB94%
Q5_K_S5.572.6 GB96%
Q5_K_M5.72.6 GB96%
Q6_K6.562.9 GB97%
Q8_08.53.7 GB100%
FP16166.5 GB100%
§ 01BENCHMARK SCORES
MMLU-PRO20.2
MATH15.3
IFEval62.9
BBH21.8
MMMU37.0
GPQA5.3
MUSR4.9