altic-dev / fluid-1-mini

Fluid-1 Mini

Experimental FluidIntelligence dictation model for local on-device use. This is a preview checkpoint, not a released model.

Model

• fluid-1-mini-q6_k.gguf
• Base architecture: Qwen3.5 ( qwen3_5 , text-only export; vision tower excluded)
• Parameters: ~2B text
• Quantization: Q6_K
• SHA-256: c5bddeb2bf46939dd2325c05a5216ff657d0cc18417c6a70a9814aa3b71243e3
• Size: 1,606,323,744 bytes
• Converted with llama.cpp b9870
• Requires a llama.cpp build with qwen35 support (b9870 or newer)

Intended use

Cleaning voice dictation into written text: filler removal, self-correction chains, punctuation, capitalization, paragraph and list formatting, and email shaping. It is not a general assistant and should not be used to answer questions.

License

This model is a Qwen3.5 derivative. The base model's terms apply.

Additional restriction by Altic: this model is licensed only for personal, non-commercial use. You may not use, copy, redistribute, host, bundle, fine-tune, sell, sublicense, or provide access to this model for any commercial, organizational, internal business, research, product, service, or revenue-generating purpose without prior written permission.

Commercial licensing is available by contacting the owner.