Granite 4 350M H is IBM's language model. IBM's 350M-parameter Granite 4 H-variant model, a hybrid architecture optimized for efficient inference in resource-constrained enterprise environments.
Specifications
Canonical IDibm-granite-4-350m-h
TypeLanguage
StatusActive
CreatorIBMIBM
Input ModalitiesText
Output ModalitiesText
Parameters0.35B
Benchmarks
Math Index
#202
MMLU-Pro
#339
GPQA
#520
HLE
#330
LiveCodeBench
#332
IFBench
#424
Time to First Token
#136
SciCode
#549
AIME 2025
#267
LCR
#470
TerminalBench Hard
#386
TAU2
#366
Output TPS
#374

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 350M H, ranked by cheapest on-demand price. The model needs about 1 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 350M H
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Granite 4.2 8B131K$0.060$0.150Available
Granite 4.1 8B131K$0.050$0.100Deprecated
Granite 4 Micro H131K——Available
Granite 4 350M H————Current
Granite 4.2 3B—131K——Available
Granite 4 350M————Available
Granite 4 H Micro————Available
Granite 4 H Small————Available
Granite 4 H Tiny————Available
Granite 4 Micro————Available
Granite 4 Nano 1B————Available

Model IDs

granite-4-0-h-350m
ibm-granite-4-350m-h