Sentence Transformers
All MiniLM L6 v2
当前
207.7M下载量4.6K点赞Aug 2021发布日期0K tokens上下文Apache 2.0许可证64 良好质量
All MiniLM L6 v2 (0.023000000044703484B parameters) requires approximately 2.1 GB of VRAM with F16 quantization. For the best balance of quality and speed, we recommend hardware with at least 3 GB of VRAM.
快速开始
— 复制粘贴即可本地运行Copy-paste commands to run All MiniLM L6 v2 on your machine.
Run
ollama run all-minilmQuick specs
Parameters0.02B
Architecturedense
Context0K tokens
Modalityembedding
Min RAM0 GB
Rec. RAM0 GB (F16)
LicenseApache 2.0
FamilyMiniLM
✓ RAG
About this model
快速推荐
最佳硬件
All MiniLM L6 v2 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 | 0.0 GB | Low | — |
Q3_K_S | 3 | 0.0 GB | Low | — |
NVFP4 | 4 | 0.0 GB | Medium | — |
Q4_K_M | 4 | 0.0 GB | Medium | — |
Q5_K_M | 5 | 0.0 GB | High | — |
Q6_K | 6 | 0.0 GB | High | — |
Q8_0 | 8 | 0.0 GB | Very High | — |
F16 | 16 | 0.0 GB | Maximum | — |
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
Weights0.0 GB
KV Cache0.3 GB
Runtime1.2 GB
Headroom0.6 GB
常见问题
FAQ — All MiniLM L6 v2
另请参阅