IBM/Dense

IBMGranite 4.1 3B

chatcodingtool_usemultilingual
3B
Parameters
512K
Context length
15
Benchmarks
6
Quantizations
0
Architecture
Dense
Released
2026-04-29
Layers
32
KV Heads
4
Head Dim
128
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 4.1 3B NOW

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

Community Ratings

Loading ratings...

Benchmarks (15)

IFEval62.9
IFBench33.7
GPQA Diamond31.4
BBH21.8
MMLU-PRO20.2
τ²-Bench19.6
MATH15.3
SciCode11.9
AA Intelligence8.5
AA Coding5.5
GPQA5.3
MUSR4.9
HLE3.4
AA Long Context3.0
Terminal-Bench2.3

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 4.1 3B

Build Hardware for Granite 4.1 3B
▸ SPEC SHEET

Granite 4.1 3B3B Dense.

▸ SPECIFICATIONS
PARAMETERS
3B
ARCHITECTURE
Dense Transformer
CONTEXT LENGTH
512K tokens
CAPABILITIES
chat, coding, tool_use, multilingual
RELEASE DATE
2026-04-29
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
GPQA5.3
MUSR4.9
GPQA Diamond31.4
HLE3.4
AA Intelligence8.5
AA Coding5.5
aa_ifbench33.7
aa_terminal_bench2.3
aa_tau219.6
aa_scicode11.9
aa_lcr3.0