What are the hardware requirements for Safety Model?

Safety Model requires approximately 3.4 GB of VRAM and supports a context window of 40K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Safety Model and how large is it?

Safety Model is developed by cs-552-2026-MMRF, a model with 1.7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Safety Model?

Safety Model is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Safety Model by cs-552-2026-MMRF — VRAM 3.4GB, 40K context

Name: Safety Model
Author: cs-552-2026-MMRF

Safety Model is an open-source language model by cs-552-2026-MMRF. Features: 1.7b LLM, VRAM: 3.4GB, Context: 40K, LLM Explorer Score: 0.24.

Base model:cs-552-2026-mmrf/15... Base model:finetune:cs-552-202... Conversational Endpoints compatible Generated from trainer Qwen3 Region:us Safetensors Tensorboard

Model Card on HF 🤗: https://huggingface.co/cs-552-2026-MMRF/safety_model

Safety Model Parameters and Internals

LLM Name	Safety Model
Repository 🤗	https://huggingface.co/cs-552-2026-MMRF/safety_model
Model Name	safety2
Base Model(s)	15kDPO cs-552-2026-MMRF/15kDPO
Model Size	1.7b
Required VRAM	3.4 GB
Updated	2026-08-03
Maintainer	cs-552-2026-MMRF
Model Type	qwen3
Model Files	3.4 GB 0.0 GB
Model Architecture	Qwen3ForCausalLM
Context Length	40960
Model Max Length	40960
Transformers Version	5.7.0
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151936
Errors	replace

Rank the Safety Model capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Safety Model

Best Alternatives	Context / RAM	Downloads	Likes
Lucy 128K	128K / 3.4 GB	123	112
Polaris 1.7B Preview	128K / 3.4 GB	73	8
DictaLM 3.0 1.7B Instruct	60K / 3.4 GB	2842	1
CORe Pico 4	40K / 3.4 GB	895	2
Qwen3 1.7B	40K / 4 GB	5633291	500
CORe Pico V3	40K / 3.4 GB	720	0
KBevo Qwen3 1.7B SFT	40K / 3.4 GB	462	0
RIFA FLASH 1.7B	40K / 3.4 GB	583	0
DualMind TKD Agentic 1.7B	40K / 3.4 GB	1798	0
Atomight V2.5 1.7B	40K / 3.4 GB	1406	1

Note: green Score (e.g. "73.2") means that the model is better than cs-552-2026-MMRF/safety_model.