Ggml-org
embeddinggemma 300M
可用数据有限 — 部分规格可能不完整或为估算值。
389.6K下载量22点赞0K tokens上下文Unknown许可证5 入门质量
embeddinggemma 300M (0.30000001192092896B parameters) requires approximately 2.1 GB of VRAM with Q6_K 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 embeddinggemma 300M on your machine.
Run
docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
--hf-repo "ggml-org/embeddinggemma-300M-GGUF" \
--hf-file "embeddinggemma-300M-GGUF-Q6_K.gguf" \
-c 4096 -ngl 99Quick specs
Parameters0.3B
Architecturedense
Context0K tokens
Modalitytext
Min RAM0.1 GB
Rec. RAM0.2 GB (Q6_K)
LicenseUnknown
FamilyGemma
✓ Chat
相关模型
快速推荐
最佳硬件
embeddinggemma 300M 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 | 0.1 GB | Low | — |
Q3_K_S | 3 | 0.1 GB | Low | — |
NVFP4 | 4 | 0.2 GB | Medium | — |
Q4_K_M | 4 | 0.2 GB | Medium | — |
Q5_K_M | 5 | 0.2 GB | High | — |
Q6_K | 6 | 0.2 GB | High | — |
Q8_0 | 8 | 0.3 GB | Very High | — |
F16 | 16 | 0.6 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
Weights0.2 GB
KV Cache0.1 GB
Runtime1.2 GB
Headroom0.6 GB
常见问题
FAQ — embeddinggemma 300M
另请参阅