Meta
Llama 3.2 3B
旧版
1.9M下载量2.2K点赞Sep 2024发布日期128K tokens上下文Community许可证32 基础质量
Llama 3.2 3B (3B parameters) requires approximately 5.3 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 7 GB of VRAM.
快速开始
— 复制粘贴即可本地运行Copy-paste commands to run Llama 3.2 3B on your machine.
Run
ollama run llama3.2Quick specs
Parameters3B
Architecturedense
Context128K tokens
Modalitytext
Min RAM1.2 GB
Rec. RAM1.8 GB (Q4_K_M)
LicenseCommunity
FamilyLlama
✓ Chat
About this model
相关模型
快速推荐
最佳硬件
Llama 3.2 3B 的最佳选择
运行此模型
量化选项
各量化级别的 VRAM 估算
No hardware detected — fit column shows raw VRAM estimates
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 1.2 GB | Low | — |
Q3_K_S | 3 | 1.5 GB | Low | — |
NVFP4 | 4 | 1.7 GB | Medium | — |
Q4_K_M | 4 | 1.8 GB | Medium | — |
Q5_K_M | 5 | 2.2 GB | High | — |
Q6_K | 6 | 2.5 GB | High | — |
Q8_0 | 8 | 3.2 GB | Very High | — |
F16 | 16 | 6.1 GB | Maximum | — |
Quality benchmarks
Llama 3.2 3B benchmark scores
Reasoning
MMLU-Pro24.4%
GPQA Diamond32.8%
MATH-50048.0%
ARC Challenge78.6%
General
Chatbot Arena—
IFEval77.4%
Source: official · 2024-09-25
硬件兼容性
全部硬件的适配估算
Computing compatibility...
内存详细分析
Reference: RTX 2060 6GB
Weights1.8 GB
KV Cache1.7 GB
Runtime1.2 GB
Headroom0.6 GB
常见问题
FAQ — Llama 3.2 3B
另请参阅