flyingfishinwater/good_and_small_models

Upload laya_multilingual_q8_0.gguf

Upload laya-Q4_K_M.gguf

Fix tokenizer.ggml.token_type: restore INT32 array type rejected by llama.cpp b10724

Fix tokenizer.ggml.token_type: restore INT32 array type rejected by llama.cpp b10724

Fix tokenizer.ggml.token_type: restore INT32 array type rejected by llama.cpp b10724

Fix tokenizer.ggml.token_type: restore INT32 array type rejected by llama.cpp b10724

Fix tokenizer.ggml.token_type: restore INT32 array type rejected by llama.cpp b10724

Rename Nanbeige_Nanbeige4.2-3B-Q4_K_M.gguf to Nanbeige4.2-3B-Q4_K_M.gguf

Add mmproj/mmproj-granite-vision-4.1-4b-Q4_K_M.gguf (llama.cpp b10724 catalog refresh)

Add granite-vision-4.1-4b-Q4_K_M.gguf (llama.cpp b10724 catalog refresh)

Add mmproj/mmproj-deepseek-ocr-2-Q4_K_M.gguf (llama.cpp b10724 catalog refresh)

Add deepseek-ocr-2-Q4_K_M.gguf (llama.cpp b10724 catalog refresh)

Add granite-4.2-3b-Q4_K_M.gguf (llama.cpp b10724 catalog refresh)

Add Nanbeige_Nanbeige4.2-3B-Q4_K_M.gguf (llama.cpp b10724 catalog refresh)

Delete PP-DocLayoutV3.onnx

Upload onnx/PP-DocLayoutV3.onnx

Delete onnx

Create onnx/

Upload PP-DocLayoutV3.onnx

Upload mmproj-PaddleOCR-VL-1.6-Q8_0.gguf

Upload PaddleOCR-VL-1.6-Q4_K_M.gguf

Upload minicpm5-1b-Q4_K_M.gguf

Delete mmproj-MiniCPM-V-4.6-Q8_0.gguf

Upload mmproj-MiniCPM-V-4.6-Q8_0.gguf

Upload 2 files

Upload 3 files

Delete Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf

Delete Qwen3.5-2B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf

Upload 2 files

Upload gliner-pii-base-v1.0_quint8.onnx

Upload 2 files

Upload mmproj-reka-edge-2603-Q8_0.gguf

Add Qwen3.5-2B-MedVL mmproj Q8_0 GGUF

Add Qwen3.5-2B-MedVL Q4_K_M GGUF

Upload mmproj-dots.ocr-Q8_0.gguf

Upload dots.ocr-Q8_0.gguf

Upload LFM2.5-VL-450M-Q8_0.gguf

Upload mmproj-LFM2.5-VL-450m-Q8_0.gguf

Upload mmproj-HunyuanOCR-Q8_0.gguf

Upload HunyuanOCR.Q4_K_M.gguf

Upload gemma-3n-E2B-it-Q4_0.gguf

Upload gemma-4-E4B-it-Q4_0.gguf

Upload gemma-4-E2B-it-Q4_0.gguf

Upload Bonsai-8B-Q1.gguf

Upload 2 files

Delete mmproj-Qwen3.5-2B-Uncensored-HauhauCS-Aggressive-f16.gguf

Delete mmproj/mmproj-Qwen2.5-VL-3B-Instruct-Q8_0.gguf

Delete mmproj/mmproj-Qwen3-VL-2B-F16.gguf

Delete mmproj/mmproj-Qwen3-VL-F16.gguf

Delete Qwen3-VL-4B-Thinking-Q4_0.gguf