Decision models · Ai2

WildGuard 7B

Name: WildGuard 7B
Author: Ai2

Task: Safety and policy checks
Returns: Fixed labels
Precision tier: 80 / 100
Size: 7.3B
Max input: 32K tokens
License: apache-2.0
Released: 2024-06

What it decides

Returns: Three yes/no answers: harmful request, response refusal, harmful response.
Checks: Prompts, replies and refusals
Languages: English
Precision: 80 / 100 · F1 0.734 in an independent 14-model comparison (arXiv 2605.28830).
Clarity: Fixed labels (12 of 15 clarity points)
How it runs: Writes a short answer · a small language model, so it runs in the same apps as LLMs.
License: apache-2.0 (Open (Apache, MIT))

Source: model card on Hugging Face (opens in a new tab) · How decision models are rated

How to run it

Original weights · Hugging Face

Full-precision files from Ai2, for fine-tuning, vLLM, Transformers.

huggingface.co/allenai/wildguard (opens in a new tab)

Free Hugging Face account needed: accept the license on the model page and the download starts right away.

Links checked 2 days ago against Hugging Face, Ollama and GitHub.

Apps that run WildGuard 7B

Our pick for each kind of computer, assuming the model fits in its memory. Pick your own GPU or Mac in the Model Finder for an exact answer.

Mac (Apple silicon)

Sentence Transformers

A few lines of Python with Transformers or Sentence Transformers; easiest for scripts and notebooks.

Also good: Docker Model Runner

Windows PC, NVIDIA GPU

Sentence Transformers

A few lines of Python with Transformers or Sentence Transformers; easiest for scripts and notebooks.

Also good: Docker Model Runner, vLLM

Windows PC, AMD Radeon

Sentence Transformers

A few lines of Python with Transformers or Sentence Transformers; easiest for scripts and notebooks.

Also good: Docker Model Runner

Linux, NVIDIA GPU

Docker Model Runner

Handy if you already work in Docker.

Also good: vLLM, Sentence Transformers

Linux server, 80 GB+ GPUs

vLLM

The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.

Also good: SGLang, Docker Model Runner

App	Type	Opens it as	Systems	Engine	Start
vLLM	Server	Original weights	WSLWindowsLinux	vLLM	`vllm serve allenai/wildguard`
SGLang	Server	Original weights	WSLWindowsLinux	SGLang	`python3 -m sglang.launch_server --model-path allenai/wildguard`
Docker Model Runner	CLI + API	Original weights	macOSWindowsLinux	llama.cpp, vLLM	`docker model run hf.co/allenai/wildguard`
Sentence Transformers	Library	Original weights	macOSWindowsLinux	PyTorch	Get Sentence Transformers

Which apps can open a model depends on the files published for it: GGUF for llama.cpp-based apps, MLX for Apple’s engine, the original weights for vLLM and SGLang. Compare every app.

Memory and speed

Each quantization on an NVIDIA GeForce RTX 4090, for one decision on a 512-token input. The best hardware table below covers other GPUs and Macs.

Format	Memory needed	Time per decision	Decisions per second	Quality	Download
`Q4_K_M`	5.3 GB	102 ms	9.8/s	76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q5_K_M`	6.0 GB	109 ms	9.2/s	77Great quality (A) · 77 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q6_K`	6.8 GB	117 ms	8.5/s	79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q8_0`	8.6 GB	135 ms	7.4/s	80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`F16`	15.4 GB	216 ms	4.6/s	80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)

One request at a time. Servers that batch (Text Embeddings Inference, vLLM, Infinity) handle many more decisions per second.

Best hardware for WildGuard 7B

The least expensive GPU in our catalog that runs it without offloading is the Intel Arc A380 (launch price $139) at Q4_K_M.

Quality	Hardware	Quant	Memory	Time per decision	Runs
80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 5090	`Q8_0`	10.2 GB / 32.0 GB	92 ms	Runs great
80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA RTX PRO 6000 Blackwell	`Q8_0`	13.4 GB / 96.0 GB	84 ms	Runs great
79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.	AMD Radeon RX 7900 XTX	`Q6_K`	8.0 GB / 24.0 GB	115 ms	Runs great
79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 4090	`Q6_K`	8.0 GB / 24.0 GB	117 ms	Runs great
79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 5080	`Q6_K`	7.6 GB / 16.0 GB	149 ms	Runs well
79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.	AMD Radeon RX 9070 XT	`Q6_K`	7.6 GB / 16.0 GB	158 ms	Runs well
79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 4080 SUPER	`Q6_K`	7.6 GB / 16.0 GB	172 ms	Runs well
79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 5070 Ti	`Q6_K`	7.6 GB / 16.0 GB	178 ms	Runs well
79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 4070 Ti SUPER	`Q6_K`	7.6 GB / 16.0 GB	197 ms	Runs well
79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 3090	`Q6_K`	8.0 GB / 24.0 GB	203 ms	Runs well

Check it on your own hardware

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.