Ggml-org
SmolVLM 500M Instruct
可用数据有限 — 部分规格可能不完整或为估算值。
509.5K下载量48点赞0K tokens上下文Unknown许可证5 入门质量
SmolVLM 500M Instruct (0.5B parameters) requires approximately 2.3 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 SmolVLM 500M Instruct on your machine.
Run
docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
--hf-repo "ggml-org/SmolVLM-500M-Instruct-GGUF" \
--hf-file "SmolVLM-500M-Instruct-GGUF-Q6_K.gguf" \
-c 4096 -ngl 99Quick specs
Parameters0.5B
Architecturedense
Context0K tokens
Modalitytext
Min RAM0.2 GB
Rec. RAM0.4 GB (Q6_K)
LicenseUnknown
FamilySmol
✓ Chat
快速推荐
最佳硬件
SmolVLM 500M Instruct 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 | 0.2 GB | Low | — |
Q3_K_S | 3 | 0.2 GB | Low | — |
NVFP4 | 4 | 0.3 GB | Medium | — |
Q4_K_M | 4 | 0.3 GB | Medium | — |
Q5_K_M | 5 | 0.4 GB | High | — |
Q6_K | 6 | 0.4 GB | High | — |
Q8_0 | 8 | 0.5 GB | Very High | — |
F16 | 16 | 1.0 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
Weights0.4 GB
KV Cache0.1 GB
Runtime1.2 GB
Headroom0.6 GB
常见问题
FAQ — SmolVLM 500M Instruct
另请参阅