Granite 4.2 3B is IBM's language model with a 131K context window. A compact reasoning-focused language model that leverages built-in chain-of-thought processing to deliver strong performance despite its small parameter count.
Specifications
Canonical IDibm-granite-4-2-3b
TypeLanguage
StatusActive
CreatorIBMIBM
Context Window131K tokens
Input ModalitiesText
Output ModalitiesText
Parameters3B
HuggingFace Likes23
HuggingFace Downloads (30d)653
HuggingFace Downloads (all-time)653
Benchmarks
Intelligence Index
#282
Coding Index
#150
GPQA
#357
HLE
#281
Time to First Token
#325
SciCode
#362
LCR
#305
Output TPS
#26

Capabilities

Input1/5
Text
Image·
Audio·
Video·
PDF·
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Cheapest Instances to Run It

Cloud GPU instances that can host Granite 4.2 3B, ranked by cheapest on-demand price. The model needs about 7 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.

All clouds
FP16 (full precision)
US Dollar ($)
Instance
Cloud
GPU
VRAM
Price
Cheapest region
Standard_NV4as_v4AzureAMD Radeon Instinct MI2516 GB$0.233/hr
g4ad.xlargeAWSRadeon Pro V5208 GB$0.379/hr
g5g.xlargeAWST4g16 GB$0.420/hr
7 more instances can run Granite 4.2 3B
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Granite 4.1 8B131K$0.050$0.100Available
Granite 4 Micro H131K$0.017$0.112Available
Granite 4.2 3B131KCurrent
Granite 4.2 8B131KAvailable
Granite 4.1 30BAvailable
Granite 4 Small H20K$0.060$0.250Available
Granite 4.1 3BAvailable
Granite 4 Nano 1B HAvailable
Granite 4 MicroAvailable
Granite 4 Nano 1BAvailable
Granite 4 350MAvailable

Model IDs

granite-4-2-3b
ibm-granite-4-2-3b
ibm-granite/granite-4.2-3b