Qwen / text-generation updated 8 months ago

Qwen3Guard-Gen-4B

Name: Qwen3Guard-Gen-4B
Author: Qwen

Qwen3Guard is a series of safety moderation models built upon Qwen3 and trained on a dataset of 1.19 million prompts and responses labeled for safety. The series includes models of three sizes (0.6B, 4B, and 8B) and features two specialized variants: Qwen3Guard-Gen, a generative model that frames safety classification as an instruction-following task, and Qwen3Guard-Stream, which incorporates a token-level classifica...

Params

4.4 B

Context

32,768

Downloads 30d

440 K

Likes

Commercial use: allowed apache-2.0 Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 10 days

440 K213 K

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	bf16	8.8 GB	10.9 GB	✅ Runs comfortably
model.safetensors (bf16, full)	bf16 + 32K ctx	8.8 GB	12.9 GB	✅ Runs comfortably

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub

~ · curl · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/qwen3guard-gen-4b
{
  "hf_id": "Qwen/Qwen3Guard-Gen-4B",
  "params_b": 4.41,
  "context_length": 32768,
  "license": { "id": "apache-2.0", "commercial": "yes" },
  "downloads_30d": 439718,
  "vram_estimates": [
    { "quant": "bf16", "gb": 10.9 }
  ],
  "updated_at": "2026-07-28T18:07:56Z"
}

est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture: Qwen3ForCausalLM
Parameters: 4.4 B
Tensor type: BF16
Context length: 32,768
Vocabulary: 151,936
Layers / heads: 36 / 32
Licence: apache-2.0
First seen on the Hub: 2025-09-23
Base model: Qwen3-4B
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Family

Base model and the most-downloaded derivatives in the catalog.

Base Qwen3-4B Qwen 4.6 M

Compare with

Qwen3-8B 16.3 M Qwen2.5-1.5B-Instruct 14.0 M Qwen2.5-7B-Instruct 12.1 M Llama-3.1-8B-Instruct 8.0 M Qwen2.5-3B-Instruct 6.0 M Qwen3-4B 4.6 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB