mlx-community/Qwen3-4B-Instruct-2507-4bit download history
mlx-community/Qwen3-4B-Instruct-2507-4bit is a 4.0B-parameter text generation model by mlx-community. In the last 30 days it was downloaded 45,843 times (9,850 in the last 7 days), and 329,551 times in total.
It ranks #3,946 on the Hub by monthly downloads and #884 among text generation models.
It has 13 likes, 1 of them in the last week.
It is a quantization of Qwen/Qwen3-4B-Instruct-2507.
15 models build on Qwen3-4B-Instruct-2507-4bit: 4 quantized, 3 fine-tuned, 8 adapters and 0 merges. Together with the original they were downloaded 47,789 times in the last 30 days. See the Qwen3-4B-Instruct-2507-4bit galaxy.
Most downloaded derivatives
- Tulifo/chittu-guard-v0-4b (finetune), 382 downloads in 30 days
- VertexAGI/prism-creative-1-5-mini (adapter), 285 downloads in 30 days
- VertexAGI/prism-creative-1-mini (adapter), 250 downloads in 30 days
- Comply2Reg/regulatory-alert-triage-qwen3-4b-v1 (finetune), 112 downloads in 30 days
- Comply2Reg/regulatory-alert-triage-qwen3-4b-v3 (finetune), 92 downloads in 30 days
- VertexAGI/refusal-bot-3000 (adapter), 89 downloads in 30 days
- latte-agent/qwen3-4b-latte-v5 (adapter), 65 downloads in 30 days
- latte-agent/qwen3-4b-latte-v6 (adapter), 62 downloads in 30 days
- GiusMagi/qwen3-4b-prosody-rag-lora-mlx (adapter), 49 downloads in 30 days
- imYChaudhary22/zen-polish-v3-4bit (quantized), 41 downloads in 30 days
- misukisu/whatsapp-twin-8bit (adapter), 26 downloads in 30 days
- kriek/fine-tuned_qwen_umig (quantized), 18 downloads in 30 days
Open mlx-community/Qwen3-4B-Instruct-2507-4bit on Hugging Face