Qwen/Qwen3-Reranker-0.6B
Full fine-tune vs Qwen/Qwen3-0.6B-Base. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Norms 106/113, MLP 84/84, Attention 112/112
34 derivatives checked
- ggml-org/Qwen3-Reranker-0.6B-Q8_0-GGUF: Quantization
- mradermacher/Qwen3-Reranker-0.6B-GGUF: Same weights, converted
- Voodisss/Qwen3-Reranker-0.6B-GGUF-llama_cpp: Same weights, converted
- pipizhao/SkillRouter-Reranker-0.6B: Partial fine-tune
- furiosa-ai/Qwen3-Reranker-0.6B: Identical copy
- drawais/Qwen3-Reranker-0.6B-AWQ-INT4: Quantization
- mku64/Qwen3-Reranker-0.6B-mlx-8Bit: Quantization
- mlx-community/Qwen3-Reranker-0.6B-4bit: Quantization
- tencent/R3-rerank-0.6b: Partial fine-tune
- DevQuasar/Qwen.Qwen3-Reranker-0.6B-GGUF: Same weights, converted
- paulalesius/Qwen3-Reranker-0.6B-GGUF: Quantization
- mradermacher/Qwen3-Reranker-0.6B-i1-GGUF: Quantization
- DuyTa/sec-rerank: Identical copy
- giladgd/Qwen3-Reranker-0.6B-GGUF: Same weights, converted
- thebajajra/RexReranker-0.6B: Full fine-tune
- ayanami-kitasan/code-pruner: LoRA-style
- batiai/Qwen3-Reranker-0.6B-GGUF: Quantization
- zhiqian99/Qwen3-Reranker-0.6B-GGUF-llama_cpp: Same weights, converted
- Nicolassuez/Qwen3-Reranker-0.6B-W8A16-g128-gptq-resident: Quantization
- RKNNAI/RK182X-EMBEDDING-Qwen3-Reranker-0.6B: Quantization
- ThakiCloud/SKILLRET-Reranker-0.6B: Partial fine-tune
- starkdmi/Qwen3-Reranker-0.6B-mlx-5bit: Quantization
- dsup2026/plumbline-0.6b: Adapter
- tatsuyaaaaaaa/Qwen3-Reranker-0.6B-gguf: Same weights, converted
- boboliu/Qwen3-Reranker-0.6B-W4A16-G128: Quantization
- dean2155/Qwen3-Reranker-0.6B-Q8_0-GGUF: Quantization
- dean2155/Qwen3-Reranker-0.6B-Q4_K_M-GGUF: Quantization
- Hanno-Labs/bosun-xs-GGUF: LoRA-style
- dolfsai/Qwen3-Reranker-0.6B-seq-cls-vllm-W8A8: Quantization
- richtext/Qwen3-Reranker-0.6B-mlx-fp16: Same weights, converted
18 other repos hold byte-for-byte identical weight files.