Working Qwen3-Reranker GGUFs (0.6B, 4B, 8B) converted with the official convert_hf_to_gguf.py. Most community conversions are broken — missing cls.out
VooDisss
Voodisss
AI & ML interests
Average Joe
Recent Activity
new activity 7 days ago
jinaai/jina-reranker-v3-GGUF:Where can I find llama-embedding and llama-tokenize? new activity about 1 month ago
huggingface/InferenceSupport:unsloth/Qwen3.5-35B-A3B-GGUF new activity about 1 month ago
ggml-org/GLM-OCR-GGUF:Critical Hallucinations and Cross-Script Confusion in Multilingual Stress Test (CJK + Cyrillic)Organizations
None yet