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
131K
支持模态
text
能力雷达图
15
general
17
coding
11
reasoning
20
science
13
agents
0
multimodal
排行榜排名
基准测试分数 (LLM Stats)
(LLM Stats (zeroeval))Code
HumanEvalOpenAI (2021)
82.4%自报
Creativity
AlpacaEval 2.0
35.2%自报
Arena Hard
26.7%自报
Finance
MMLU
60.4%自报
TruthfulQA
58.1%自报
General
IFEvalGoogle Research (2023)
63.0%自报
PopQA
22.9%自报
Language
BIG-Bench Hard
55.7%自报
Math
GSM8k
70.1%自报
DROP
46.2%自报
Reasoning
HumanEval+
78.3%自报
Safety
AttaQ
86.1%自报
AA 评测指数
(Artificial Analysis)Math Index(Artificial Analysis)6.0
Intelligence Index(Artificial Analysis)2.0
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))0.4
Gpqa(NYU + Cohere + Anthropic (2023))0.3
Ifbench(Google Research (2023))0.2
Livecodebench(UC Berkeley + MIT + Cornell (2024))0.2
Tau2(Sierra + U Toronto + Vector Institute (2025))0.1
Scicode(UIUC + Argonne National Lab (2024))0.1
Aime 25(MAA (Mathematical Association of America))0.1
Lcr(Artificial Analysis)0.1
Hle(Center for AI Safety + Scale AI (2025))0.1
Terminalbench Hard(Stanford × Laude Institute (2026))0.0
LLM Stats 分类评分
(LLM Stats (zeroeval))Safety90
Code80
Legal60
Math60
Structured Output60
Instruction Following60
Language60
Finance60
General60
Healthcare60
Reasoning50
Creativity30
Writing30
定价
输入价格免费
输出价格免费
混合价格(3:1)免费
速度
Tokens/秒0.0
首Token延迟0.00s
首回答延迟0.00s
供应商价格排行
供应商价格排行
2 个供应商
最便宜: OpenRouter最贵: Kilo Gateway
供应商输入输出
1OpenRouter最便宜
$0.017
$0.112
2Kilo Gateway
$0.017
$0.112
比较该模型在不同 API 供应商之间的定价。