4b-1.8gb : GGUF

• For text only LLMs: llama-cli -hf mypersonalpf1/4b-1.8gb --jinja
• For multimodal models: llama-mtmd-cli -hf mypersonalpf1/4b-1.8gb --jinja

Available Model files:

• unsloth_Qwen3.5-4B_1786886791.Q2_K_L.gguf
• unsloth_Qwen3.5-4B_1786886791.BF16-mmproj.gguf This was trained 2x faster with Unsloth