Llama 3.2 Instruct 3B
MetaLlama开源权重Llama 3.2 Community License
描述
Llama 3.2 3B Instruct is a large language model that supports a context length of 128K tokens and are state-of-the-art in their class for on-device use cases like summarization, instruction following, and rewriting tasks running locally at the edge.
发布日期
2024-09-25
参数规模
3.2B
上下文长度
131K
支持模态
text
能力雷达图
14
general
8
coding
13
reasoning
19
science
50
agents
0
multimodal
排行榜排名
基准测试分数 (LLM Stats)
(LLM Stats (zeroeval))Chat
IFEvalGoogle Research (2023)
77.4%自报
General
BFCL v2
67.0%自报
MMLU
63.4%自报
Nexus
34.3%自报
Language
Open-rewrite
40.1%自报
Long Context
NIH/Multi-needle
84.7%自报
InfiniteBench/En.MC
63.3%自报
InfiniteBench/En.QA
19.8%自报
Math
GSM8k
77.7%自报
MGSM
58.2%自报
MATH
48.0%自报
Reasoning
ARC-C
78.6%自报
HellaSwagAI2 (2019)
69.8%自报
GPQANYU + Cohere + Anthropic (2023)
32.8%自报
Summarization
TLDR9+ (test)
19.0%自报
AA 评测指数
(Artificial Analysis)Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))48.9
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))34.7
Ifbench(Google Research (2023))26.2
Gpqa(NYU + Cohere + Anthropic (2023))25.5
Tau2(Sierra + U Toronto + Vector Institute (2025))21.1
Livecodebench(UC Berkeley + MIT + Cornell (2024))8.3
Aime(MAA (Mathematical Association of America))6.7
Intelligence Index(Artificial Analysis)5.7
Hle(Center for AI Safety + Scale AI (2025))5.3
Lcr(Artificial Analysis)4.3
Aime 25(MAA (Mathematical Association of America))3.3
Math Index(Artificial Analysis)3.3
LLM Stats 分类评分
(LLM Stats (zeroeval))Chat80
Instruction Following80
Structured Output80
Language60
Legal60
Math60
Reasoning60
Finance60
General60
Healthcare60
Tool Calling50
Physics30
Biology30
Chemistry30
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
4 个供应商
最便宜: NovitaAI最贵: Kilo Gateway
供应商输入输出
1NovitaAI最便宜
$0.03
$0.05
2NanoGPT
$0.0306
$0.0493
3OpenRouter
$0.05
$0.33
4Kilo Gateway
$0.05
$0.33
比较该模型在不同 API 供应商之间的定价。