Granite 4.0 Micro
IBM開源權重Apache 2.0 · 商用許可
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.
發布日期
2025-09-22
參數規模
7.0B
上下文長度
131K
支援模態
text
能力雷達圖
15
general
17
coding
11
reasoning
20
science
13
agents
0
multimodal
排行榜排名
基準測試分數 (LLM Stats)
(LLM Stats (zeroeval))Code
HumanEvalOpenAI (2021)
82.4%自報
Creativity
AlpacaEval 2.0
35.2%自報
Arena Hard
26.7%自報
Finance
MMLU
60.4%自報
TruthfulQA
58.1%自報
General
IFEvalGoogle Research (2023)
63.0%自報
PopQA
22.9%自報
Language
BIG-Bench Hard
55.7%自報
Math
GSM8k
70.1%自報
DROP
46.2%自報
Reasoning
HumanEval+
78.3%自報
Safety
AttaQ
86.1%自報
AA 評測指數
(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 分類評分
(LLM Stats (zeroeval))Safety90
Code80
Legal60
Math60
Structured Output60
Instruction Following60
Language60
Finance60
General60
Healthcare60
Reasoning50
Creativity30
Writing30
定價
輸入價格免費
輸出價格免費
混合價格(3:1)免費
速度
Tokens/秒0.0
首Token延遲0.00s
首回答延遲0.00s
供應商價格排行
供應商價格排行
2 個供應商
最便宜: OpenRouter最貴: Kilo Gateway
供應商輸入輸出
1OpenRouter最便宜
$0.017
$0.112
2Kilo Gateway
$0.017
$0.112
比較該模型在不同 API 供應商之間的定價。