IBM/Mixture of Experts

Granite 4.0 Small

Granite 4.0 Small — strong enterprise MoE model with multilingual support.

chatcodingmultilingualThinkingTool Use

32B

Parameters (8B active)

125K

Context length

6

Benchmarks

14

Quantizations

40K

HF downloads

Architecture

MoE

Released

2025-10-02

Layers

40

KV Heads

8

Head Dim

128

Family

granite

Quantization Options

Quant	Bits	VRAM	Quality
IQ3_XXS	3.25	13.5 GB	low
IQ3_XS	3.5	14.5 GB	low
Q3_K_S	3.64	15.0 GB	low
IQ3_M	3.76	15.5 GB	low
Q3_K_M	4	16.5 GB	low
Q3_K_L	4.3	17.7 GB	moderate
IQ4_XS	4.46	18.3 GB	moderate
Q4_K_S	4.67	19.2 GB	moderate
Q4_K_M	4.89	20.0 GB	good
Q5_K_S	5.57	22.8 GB	good
Q5_K_M	5.7	23.3 GB	good
Q6_K	6.56	26.7 GB	excellent
Q8_0	8.5	34.5 GB	lossless
FP16	16	64.5 GB	lossless

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 SMALL NOW

Rent on RunPod →Or Vast.ai →

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

Community Ratings

Loading ratings...

Benchmarks (6)

HumanEval88.0

IFEval87.6

MBPP84.0

BBH81.6

BigCodeBench46.2

GPQA40.6

Run this model

▸Easiest way to get started·Beginners

curl -fsSL https://ollama.com/install.sh | sh

$ollama run granite:32b-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

HuggingFace GGUF Downloads Build Hardware

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

NVIDIA RTX 4090

24 GB VRAM • 1008 GB/s

NVIDIA

$1599

Amazon Newegg eBay PCPartPicker

NVIDIA RTX 3090 Ti

24 GB VRAM • 1008 GB/s

NVIDIA

$999

Amazon Newegg eBay PCPartPicker

NVIDIA RTX 3090

24 GB VRAM • 936 GB/s

NVIDIA

$850

Amazon Newegg eBay PCPartPicker

AMD RX 7900 XTX

24 GB VRAM • 960 GB/s

AMD

$999

Amazon Newegg eBay PCPartPicker

Apple M4 Pro (24GB)

24 GB VRAM • 273 GB/s

APPLE

$1399

24 GB VRAM • 300 GB/s

NVIDIA

$2500

NVIDIA A10 24GB

24 GB VRAM • 600 GB/s

NVIDIA

$3500

Amazon Newegg eBay PCPartPicker

Apple M2 (24GB)

24 GB VRAM • 100 GB/s

APPLE

$999

Apple M3 (24GB)

24 GB VRAM • 100 GB/s

APPLE

$999

Apple M4 (24GB)

24 GB VRAM • 120 GB/s

APPLE

$699

NVIDIA Tesla M40 24 GB

24 GB VRAM • 288 GB/s

NVIDIA

NVIDIA Tesla P10

24 GB VRAM • 694 GB/s

NVIDIA

NVIDIA Tesla P40

24 GB VRAM • 347 GB/s

NVIDIA

NVIDIA Quadro RTX 6000

24 GB VRAM • 672 GB/s

NVIDIA

$4000

Amazon Newegg eBay PCPartPicker

NVIDIA Quadro RTX 6000 Passive

24 GB VRAM • 624 GB/s

NVIDIA

$4000

Amazon Newegg eBay PCPartPicker

NVIDIA GeForce RTX 3090

24 GB VRAM • 936 GB/s

NVIDIA

$1499

Amazon Newegg eBay PCPartPicker

NVIDIA A10 PCIe

24 GB VRAM • 600 GB/s

NVIDIA

Amazon Newegg eBay PCPartPicker

24 GB VRAM • 600 GB/s

NVIDIA

Amazon Newegg eBay PCPartPicker

NVIDIA RTX A5000

24 GB VRAM • 768 GB/s

NVIDIA

$2500

NVIDIA GeForce RTX 3090 Ti

24 GB VRAM • 1010 GB/s

NVIDIA

$1999

Amazon Newegg eBay PCPartPicker

NVIDIA GeForce RTX 4090

24 GB VRAM • 1010 GB/s

NVIDIA

$1599

Amazon Newegg eBay PCPartPicker

24 GB VRAM • 864 GB/s

NVIDIA

$5000

24 GB VRAM • 864 GB/s

NVIDIA

$5000

AMD Radeon RX 7900 XTX

24 GB VRAM • 960 GB/s

AMD

$999

Amazon Newegg eBay PCPartPicker

NVIDIA GeForce RTX 4090 D

24 GB VRAM • 1010 GB/s

NVIDIA

$1599

Amazon Newegg eBay PCPartPicker

NVIDIA GeForce RTX 5090 D V2

24 GB VRAM • 1340 GB/s

NVIDIA

$1999

Amazon Newegg eBay PCPartPicker

NVIDIA TITAN RTX

24 GB VRAM • 672 GB/s

NVIDIA

Amazon Newegg eBay PCPartPicker

NVIDIA A30 PCIe

24 GB VRAM • 933 GB/s

NVIDIA

Amazon Newegg eBay PCPartPicker

24 GB VRAM • 1220 GB/s

NVIDIA

Amazon Newegg eBay PCPartPicker

NVIDIA PG506-207

24 GB VRAM • 933 GB/s

NVIDIA

Amazon Newegg eBay PCPartPicker

Find the best GPU for Granite 4.0 Small

Build Hardware for Granite 4.0 Small

Model Card

View on HuggingFace

Granite 4.0 Small — strong enterprise MoE model with multilingual support.

▸ SPEC SHEET

Granite 4.0 Small — 32B MoE.

▸ SPECIFICATIONS

PARAMETERS: 32B (8B active)
ARCHITECTURE: Mixture of Experts
CONTEXT LENGTH: 125K tokens
CAPABILITIES: chat, coding, multilingual
RELEASE DATE: 2025-10-02
PROVIDER: IBM
FAMILY: granite

▸ VRAM REQUIREMENTS

QUANT	BPW	VRAM	QUALITY
IQ3_XXS	3.25	13.5 GB	82%
IQ3_XS	3.5	14.5 GB	84%
Q3_K_S	3.64	15.0 GB	85%
IQ3_M	3.76	15.5 GB	86%
Q3_K_M	4	16.5 GB	88%
Q3_K_L	4.3	17.7 GB	90%
IQ4_XS	4.46	18.3 GB	92%
Q4_K_S	4.67	19.2 GB	93%
Q4_K_M	4.89	20.0 GB	94%
Q5_K_S	5.57	22.8 GB	96%
Q5_K_M	5.7	23.3 GB	96%
Q6_K	6.56	26.7 GB	97%
Q8_0	8.5	34.5 GB	100%
FP16	16	64.5 GB	100%

§ 01BENCHMARK SCORES

HumanEval88.0

IFEval87.6

BBH81.6

GPQA40.6

MBPP84.0

BigCodeBench46.2

§ 03COMPATIBLE GPUs

30 @ Q4_K_M

NVIDIA RTX 4090

24 GB · 1008 GB/s

NVIDIA RTX 3090 Ti

24 GB · 1008 GB/s

NVIDIA RTX 3090

24 GB · 936 GB/s

AMD RX 7900 XTX

24 GB · 960 GB/s

Apple M4 Pro (24GB)

24 GB · 273 GB/s

24 GB · 300 GB/s

NVIDIA A10 24GB

24 GB · 600 GB/s

Apple M2 (24GB)

24 GB · 100 GB/s

Apple M3 (24GB)

24 GB · 100 GB/s

Apple M4 (24GB)

24 GB · 120 GB/s

NVIDIA Tesla M40 24 GB

24 GB · 288 GB/s

NVIDIA Tesla P10

24 GB · 694 GB/s

NVIDIA Tesla P40

24 GB · 347 GB/s

NVIDIA Quadro RTX 6000

24 GB · 672 GB/s

NVIDIA Quadro RTX 6000 Passive

24 GB · 624 GB/s