zesima-v0 : GGUF

• For text only LLMs: ./llama.cpp/llama-cli -hf awilliamson/zesima-v0 --jinja
• For multimodal models: ./llama.cpp/llama-mtmd-cli -hf awilliamson/zesima-v0 --jinja

Available Model files:

• qwen3-vl-2b-thinking.Q4_K_M.gguf
• qwen3-vl-2b-thinking.F16-mmproj.gguf This was trained 2x faster with Unsloth