Granite 4.0 Micro
IBM开源权重Apache 2.0 · 商用许可
描述
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.
发布日期
2025-09-22
参数规模
7.0B
上下文长度
—
支持模态
—
能力雷达图
60
general
80
coding
60
reasoning
51
science估算
66
agents
0
multimodal
缺少专门科学评测时,Science 由 LLM Stats 科学得分或推理能力估算。
排行榜排名
暂无排名数据
基准测试分数 (LLM Stats)
(LLM Stats (zeroeval))Chat
IFEvalGoogle Research (2023)
63.0%自报
General
MMLU
60.4%自报
TruthfulQA
58.1%自报
AlpacaEval 2.0
35.2%自报
Arena Hard
26.7%自报
PopQA
22.9%自报
Math
GSM8k
70.1%自报
Reasoning
HumanEvalOpenAI (2021)
82.4%自报
HumanEval+
78.3%自报
BIG-Bench Hard
55.7%自报
DROP
46.2%自报
Safety
AttaQ
86.1%自报
AA 评测指数
(Artificial Analysis)暂无 AA 评测数据
LLM Stats 分类评分
(LLM Stats (zeroeval))Safety90
Code80
Instruction Following60
Language60
Legal60
Math60
Structured Output60
Finance60
General60
Healthcare60
Reasoning50
Chat40
Creativity30
Writing30
定价
暂无定价数据
速度
暂无速度数据
供应商价格排行
暂无提供商数据