Qari-OCR-0.4.0-VL-4B-Instruct-GGUF : GGUF

• For text only LLMs: llama-cli -hf marwan-osama/Qari-OCR-0.4.0-VL-4B-Instruct-GGUF --jinja
• For multimodal models: llama-mtmd-cli -hf marwan-osama/Qari-OCR-0.4.0-VL-4B-Instruct-GGUF --jinja

Available Model files:

• Qwen3-VL-4B-Instruct.Q8_0.gguf
• Qwen3-VL-4B-Instruct.F16-mmproj.gguf This was trained 2x faster with Unsloth