Qwen3-4B-SafeRL-GGUF

Qwen3-4B-SafeRL is a safety-aligned version of the Qwen3-4B model, trained using Reinforcement Learning (RL) with a reward signal from Qwen3Guard-Gen to boost robustness against harmful or adversarial prompts. This safety alignment process optimizes the model with a hybrid reward function that simultaneously focuses on three objectives: maximizing safety (penalizing unsafe content as detected by Qwen3Guard-Gen-4B), maximizing helpfulness (rewarding genuinely helpful responses based on the WorldPM-Helpsteer2 model), and minimizing unnecessary refusals (penalizing unnecessary refusals according to Qwen3Guard-Gen-4B).

Model Files

File Name	Quant Type	File Size
Qwen3-4B-SafeRL.BF16.gguf	BF16	8.05 GB
Qwen3-4B-SafeRL.F16.gguf	F16	8.05 GB
Qwen3-4B-SafeRL.F32.gguf	F32	16.1 GB
Qwen3-4B-SafeRL.Q2_K.gguf	Q2_K	1.67 GB
Qwen3-4B-SafeRL.Q3_K_L.gguf	Q3_K_L	2.24 GB
Qwen3-4B-SafeRL.Q3_K_M.gguf	Q3_K_M	2.08 GB
Qwen3-4B-SafeRL.Q3_K_S.gguf	Q3_K_S	1.89 GB
Qwen3-4B-SafeRL.Q4_K_M.gguf	Q4_K_M	2.5 GB
Qwen3-4B-SafeRL.Q4_K_S.gguf	Q4_K_S	2.38 GB
Qwen3-4B-SafeRL.Q5_K_M.gguf	Q5_K_M	2.89 GB
Qwen3-4B-SafeRL.Q5_K_S.gguf	Q5_K_S	2.82 GB
Qwen3-4B-SafeRL.Q6_K.gguf	Q6_K	3.31 GB
Qwen3-4B-SafeRL.Q8_0.gguf	Q8_0	4.28 GB

Quants Usage

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):