Model reference · open weights
ShieldLM-chatglm3 is an open-weight embedding model from thu-coai. ShieldLM-6B-chatglm3 (FP16) weighs 12.5 GB; the smallest configuration that runs it is RTX 4060 Ti 16 GB.
For self-hosting, compare this build's requirements below with the GPU you plan to rent.
Summary of the thu-coai/ShieldLM-6B-chatglm3 model card, 2026-10-01
What it is
| Released by | thu-coai |
|---|---|
| Released | 2024-02-26 |
| Parameters | 6.2B |
| VRAM | 12.5 GB for the weights |
What it runs on
| Card | Runs | Memory |
|---|---|---|
| RTX 3060 12 GB | does not fit | 11.6 GB |
| RTX 4060 Ti 16 GB | tight | 15.4 GB |
| RTX 3090 24 GB | fits | 23.4 GB |
| RTX 4090 24 GB | fits | 23.4 GB |
| RTX 5090 32 GB | fits | 31.0 GB |
| L40S 48 GB | fits | 44.0 GB |
| A100 80 GB | fits | 78.2 GB |
| H100 80 GB | fits | 78.1 GB |
| RTX PRO 6000 Blackwell 96 GB | fits | 93.8 GB |
| DGX Spark (GB10) 128 GB unified | fits | 107 GB |
| H200 141 GB | fits | 138 GB |
| B200 180 GB | fits | 176 GB |
From the model card
The ShieldLM model (paper link) initialized from chatglm3-6b. ShieldLM is a bilingual (Chinese and English) safety detector that mainly aims to help to detect safety issues in LLMs' generations. It aligns with general human safety standards, supports fine-grained customizable detection rules, and provides explanations for its decisions. Refer to our github repository for more detailed information.
Please refer to our github repository for the detailed usage instructions.
ShieldLM demonstrates impressive detection performance across 4 ID and OOD test sets, compared to strong baselines such as GPT-4, Llama Guard and Perspective API. Refer to our paper for more detailed evaluation results.
Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.