Nemotron-3-Nano-4B : GGUF

• For text only LLMs: llama-cli -hf andersonscode/Nemotron-3-Nano-4B --jinja
• For multimodal models: llama-mtmd-cli -hf andersonscode/Nemotron-3-Nano-4B --jinja

Available Model files:

• NVIDIA-Nemotron-3-Nano-4B.Q8_0.gguf
• NVIDIA-Nemotron-3-Nano-4B.Q4_K_M.gguf This was trained 2x faster with Unsloth