Granite 4 Nano 1B is IBM's language model. A 1B-parameter ultra-compact LLM from IBM's Granite 4 family, designed for efficient on-device and edge inference.
Specifications
Canonical IDibm-granite-4-nano-1b
TypeLanguage
StatusActive
CreatorIBMIBM
Input ModalitiesText
Output ModalitiesText
Parameters1B
Benchmarks
Intelligence Index
#545
Math Index
#248
MMLU-Pro
#327
GPQA
#509
HLE
#412
LiveCodeBench
#326
IFBench
#415
Time to First Token
#170
SciCode
#499
AIME 2025
#248
LCR
#417
TerminalBench Hard
#390
TAU2
#309
Output TPS
#408

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 Nano 1B, ranked by cheapest on-demand price. The model needs about 2 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
g6f.largeAWSL43 GB$0.202/hr
Standard_NV4as_v4AzureAMD Radeon Instinct MI2516 GB$0.233/hr
g6f.xlargeAWSL43 GB$0.237/hr
7 more instances can run Granite 4 Nano 1B
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Granite 4 Nano 1B————Current
Granite 4 Nano 1B H————Available

Other Models

ModelTierReleasedContextInput / 1MOutput / 1M
Granite 4.2 8B—131K$0.060$0.150
Granite 4.1 8B—131K$0.050$0.100
Granite 4 Micro HMicro131K$0.017$0.112
Granite 4.2 30B——131K——
Granite 4.2 3B——131K——
Granite 4.1 30B—————
Granite 4.1 3B—————
Granite 4 350M—————
Granite 4 MicroMicro————
Granite 4 Small HSmall—131K$0.064$0.265

Model IDs

granite-4-0-h-nano-1b
granite-4-0-nano-1b
ibm-granite-4-nano-1b