Decision models · Alibaba

Qwen3Guard Gen 0.6B

Name: Qwen3Guard Gen 0.6B
Author: Alibaba

Task: Safety and policy checks
Returns: Fixed labels
Precision tier: 74 / 100
Size: 750M
Max input: 32K tokens
License: apache-2.0
Released: 2025-09

What it decides

Returns: Safe, Controversial or Unsafe, plus categories and a refusal flag.
Checks: Prompts and replies
Languages: 119 languages
Precision: 74 / 100 · Smallest Qwen3Guard; same labels as the 8B with lower accuracy.
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

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

huggingface.co/mradermacher/Qwen3Guard-Gen-0.6B-GGUF (opens in a new tab)

ollama run hf.co/mradermacher/Qwen3Guard-Gen-0.6B-GGUF

Original weights · Hugging Face

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

huggingface.co/Qwen/Qwen3Guard-Gen-0.6B (opens in a new tab)

No sign-in needed.

Links checked 3 days ago against Hugging Face, Ollama and GitHub.

Apps that run Qwen3Guard Gen 0.6B

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)

LM Studio

Runs the MLX build, typically 35–90% faster than GGUF for a model with 0.8B active parameters on Apple silicon.

Also good: MLX LM, Unsloth Desktop

Windows PC, NVIDIA GPU

LM Studio

Point-and-click: search, download and chat in one window.

Also good: llama.cpp, Ollama

Windows PC, AMD Radeon

Lemonade

AMD’s own app: llama.cpp tuned for Radeon on Vulkan and ROCm.

Also good: LM Studio, llama.cpp

Linux, NVIDIA GPU

LM Studio

Point-and-click: search, download and chat in one window.

Also good: llama.cpp, Ollama

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: LM Studio, SGLang

App	Type	Opens it as	Systems	Engine	Start
LM Studio	Desktop app	GGUF or MLX	macOSWindowsLinux	llama.cpp, MLX	Open in LM Studio
Ollama	CLI + API	GGUF from Hugging Face	macOSWindowsLinux	llama.cpp, MLX	`ollama run hf.co/mradermacher/Qwen3Guard-Gen-0.6B-GGUF:Q4_K_M`
llama.cpp	CLI + API	GGUF	macOSWindowsLinux	llama.cpp	`llama-server -hf mradermacher/Qwen3Guard-Gen-0.6B-GGUF:Q4_K_M`
Jan	Desktop app	GGUF or MLX	macOSWindowsLinux	llama.cpp, MLX	Open in Jan
MLX LM	CLI + API	MLX	macOS	MLX	`mlx_lm.chat --model mlx-community/Qwen3Guard-Gen-0.6B-MLX`
vLLM	Server	Original weights	WSLWindowsLinux	vLLM	`vllm serve Qwen/Qwen3Guard-Gen-0.6B`
SGLang	Server	Original weights	WSLWindowsLinux	SGLang	`python3 -m sglang.launch_server --model-path Qwen/Qwen3Guard-Gen-0.6B`
Docker Model Runner	CLI + API	GGUF	macOSWindowsLinux	llama.cpp, vLLM	`docker model run hf.co/mradermacher/Qwen3Guard-Gen-0.6B-GGUF:Q4_K_M`
Lemonade	Desktop app	GGUF	macOSWindowsLinux	llama.cpp, ONNX Runtime GenAI	`lemonade pull mradermacher/Qwen3Guard-Gen-0.6B-GGUF:Q4_K_M`
Unsloth Desktop	Desktop app	GGUF or MLX	macOSWindowsLinux	llama.cpp, MLX, stable-diffusion.cpp	Open in Unsloth Desktop
Atomic Chat	Desktop app	GGUF or MLX	macOSWindowsLinux	llama.cpp, MLX-VLM	Open in Atomic Chat
LocalAI	Server	GGUF	macOSWSLWindowsLinux	llama.cpp, rerankers, Transformers	Get LocalAI
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`	1.3 GB	14 ms	71/s	70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	1.4 GB	15 ms	67/s	71Great quality (A) · 71 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	1.4 GB	16 ms	64/s	73Great quality (A) · 73 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.	GGUF (opens in a new tab)
`Q8_0`	1.6 GB	18 ms	57/s	74Great quality (A) · 74 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.	GGUF (opens in a new tab)
`F16`	2.3 GB	26 ms	39/s	74Great quality (A) · 74 of 100: how capable the model is at F16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab) 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 Qwen3Guard Gen 0.6B

The least expensive GPU in our catalog that runs it without offloading is the Intel Arc A380 (launch price $139) at Q6_K.

Quality	Hardware	Quant	Memory	Time per decision	Runs
74Great quality (A) · 74 of 100: how capable the model is at F16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	AMD Radeon RX 7900 XTX	`F16`	3.5 GB / 24.0 GB	28 ms	Runs great
74Great quality (A) · 74 of 100: how capable the model is at F16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	AMD Radeon RX 9070 XT	`F16`	3.1 GB / 16.0 GB	39 ms	Runs great
74Great quality (A) · 74 of 100: how capable the model is at F16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	AMD Ryzen AI Max+ 395 (128 GB)	`F16`	10.0 GB / 96.0 GB	85 ms	Runs great
74Great quality (A) · 74 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.	Apple M1 Max (64 GB)	`Q8_0`	5.5 GB / 48.0 GB	84 ms	Runs great
74Great quality (A) · 74 of 100: how capable the model is at F16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	Apple M2 Ultra (192 GB)	`F16`	13.9 GB / 144 GB	49 ms	Runs great
74Great quality (A) · 74 of 100: how capable the model is at F16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	Apple M3 Ultra (256 GB)	`F16`	17.7 GB / 192 GB	48 ms	Runs great
74Great quality (A) · 74 of 100: how capable the model is at F16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	Apple M3 Ultra (512 GB)	`F16`	33.1 GB / 384 GB	48 ms	Runs great
74Great quality (A) · 74 of 100: how capable the model is at F16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	Apple M4 Max (128 GB)	`F16`	10.0 GB / 96.0 GB	71 ms	Runs great
74Great quality (A) · 74 of 100: how capable the model is at F16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	Apple M4 Max (64 GB)	`F16`	6.2 GB / 48.0 GB	71 ms	Runs great
74Great quality (A) · 74 of 100: how capable the model is at F16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	Intel Arc B580	`F16`	2.9 GB / 12.0 GB	74 ms	Runs great

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.