The Qwen/Qwen3-8B-Base galaxy

7,605 models are built on Qwen/Qwen3-8B-Base: 1,709 quantized, 3,667 fine-tuned, 2,168 adapters and 61 merges. Together they were downloaded 22,004,214 times in the last 30 days.

Most downloaded direct derivatives

• Qwen/Qwen3-8B (finetune), 10.7M downloads in 30 days
• Qwen/Qwen3-Embedding-8B (finetune), 2.6M downloads in 30 days
• Qwen/Qwen3-Reranker-8B (finetune), 426.4K downloads in 30 days
• Qwen/Qwen3-Embedding-8B-GGUF (quantized), 31.1K downloads in 30 days
• unsloth/Qwen3-8B-Base-unsloth-bnb-4bit (quantized), 6.9K downloads in 30 days
• zeromodels/qwen3-8b-base (finetune), 5.1K downloads in 30 days
• unsloth/Qwen3-8B-Base-bnb-4bit (quantized), 3.4K downloads in 30 days
• snuh/hari-q3-8b (finetune), 3K downloads in 30 days
• unsloth/Qwen3-8B-Base (finetune), 2.8K downloads in 30 days
• hkust-nlp/drkernel-8b-coldstart (finetune), 2.3K downloads in 30 days
• mradermacher/Qwen3-8B-Base-GGUF (quantized), 2K downloads in 30 days
• Mungert/Qwen3-Reranker-8B-GGUF (quantized), 1.6K downloads in 30 days
• QuantFactory/Qwen3-8B-GGUF (quantized), 1.3K downloads in 30 days
• formalmathatepfl/qwen3-sft-feedback-with-proof-repair-rl (finetune), 1.3K downloads in 30 days
• unsloth/Qwen3-Embedding-8B (finetune), 1.1K downloads in 30 days
• QuantFactory/Qwen3-Reranker-8B-GGUF (quantized), 969 downloads in 30 days
• mkd-hossain/Keural-Cortex-8B-64K (finetune), 969 downloads in 30 days
• mradermacher/Qwen3-8B-Base-i1-GGUF (quantized), 925 downloads in 30 days
• Mungert/Qwen3-8B-GGUF (quantized), 922 downloads in 30 days
• mlx-community/Qwen3-Embedding-8B-mxfp8 (finetune), 875 downloads in 30 days
• Qwen/SAE-Res-Qwen3-8B-Base-W64K-L0_100 (finetune), 840 downloads in 30 days
• Mungert/Qwen3-Embedding-8B-GGUF (quantized), 825 downloads in 30 days
• Hyukkyu/Qwen3-8B-Base-RAQUEL-MUSE-M-orig-LoRA-v1 (finetune), 764 downloads in 30 days
• FreedomIntelligence/HuatuoGPT-3-8B (finetune), 762 downloads in 30 days
• Hyukkyu/Qwen3-8B-Base-RAQUEL-MUSE-M-ret-LoRA-v1 (finetune), 688 downloads in 30 days