FitMyLLM
IBM/Dense

IBMGranite Vision 4.1 4B

Granite Vision 4.1 4B — IBM's small vision-language model, tuned for documents, charts and tables rather than general image chat.

chatvisionmultilingual
4B
Parameters
128K
Context length
0
Benchmarks
6
Quantizations
155K
HF downloads
Architecture
Dense
Released
2026-04-16
Layers
40
KV Heads
8
Head Dim
64
Family
granite

Quantization Options

Context length:
QuantBitsVRAM @ 16KQuality
Q4_K_M4.89
3.9 GB
2.9 + 0.9 KV
good
Q5_K_S5.57
4.2 GB
3.3 + 0.9 KV
good
Q5_K_M5.7
4.3 GB
3.3 + 0.9 KV
good
Q6_K6.56
4.7 GB
3.8 + 0.9 KV
excellent
Q8_08.5
5.7 GB
4.7 + 0.9 KV
lossless
FP1616
9.4 GB
8.5 + 0.9 KV
lossless

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

Deploying for a team or in production? Size GPUs, cost & scaling in Enterprise →
READY TO RUN THIS?RENT BY THE HOUR

RENT A GPU AND RUN GRANITE VISION 4.1 4B NOW

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

Community Ratings

Loading ratings...

Run this model

Easiest way to get started·Beginners
DOCS ↗
curl -fsSL https://ollama.com/install.sh | sh
$ollama run granite:4b-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 Vision 4.1 4B

Build Hardware for Granite Vision 4.1 4B
▸ SPEC SHEET

Granite Vision 4.1 4B4B Dense.

▸ SPECIFICATIONS
PARAMETERS
4B
ARCHITECTURE
Dense Transformer
CONTEXT LENGTH
128K tokens
CAPABILITIES
chat, vision, multilingual
RELEASE DATE
2026-04-16
PROVIDER
IBM
FAMILY
granite
▸ VRAM REQUIREMENTS
QUANTBPWVRAMQUALITY
Q4_K_M4.892.9 GB94%
Q5_K_S5.573.3 GB96%
Q5_K_M5.73.3 GB96%
Q6_K6.563.8 GB97%
Q8_08.54.7 GB100%
FP16168.5 GB100%
§ 03COMPATIBLE GPUs
30 @ Q4_K_M