Granite 4.0 Micro
IBMOpen WeightApache 2.0 · Commercial OK
Description
A preliminary version of the smallest model in the upcoming Granite 4.0 family, released May 2025. It utilizes a novel hybrid Mamba-2/Transformer, fine-grained mixture of experts (MoE) architecture (7B total parameters, 1B active at inference). This preview version is partially trained (2.5T tokens) but demonstrates significant memory efficiency and performance potential, validated for at least 128K context length without positional encoding.
Release Date
2025-09-22
Parameters
7.0B
Context Length
—
Modalities
—
Capability Radar
60
general
80
coding
60
reasoning
51
scienceest.
66
agents
0
multimodal
Science is estimated from LLM Stats science scores or reasoning when no dedicated science benchmarks are available.
Rankings
No ranking data available
Benchmark Scores (LLM Stats)
(LLM Stats (zeroeval))Chat
IFEvalGoogle Research (2023)
63.0%SR
General
MMLU
60.4%SR
TruthfulQA
58.1%SR
AlpacaEval 2.0
35.2%SR
Arena Hard
26.7%SR
PopQA
22.9%SR
Math
GSM8k
70.1%SR
Reasoning
HumanEvalOpenAI (2021)
82.4%SR
HumanEval+
78.3%SR
BIG-Bench Hard
55.7%SR
DROP
46.2%SR
Safety
AttaQ
86.1%SR
AA Evaluation Indices
(Artificial Analysis)No AA evaluation data available
LLM Stats Category Scores
(LLM Stats (zeroeval))Safety90
Code80
Instruction Following60
Language60
Legal60
Math60
Structured Output60
Finance60
General60
Healthcare60
Reasoning50
Chat40
Creativity30
Writing30
Pricing
No pricing data available
Speed
No speed data available
Provider Price Ranking
No provider data available