Minico M1 1105 GGUF

GGUF builds of Mincofficial/Minico-M1-1105, a 350M reasoning model with five effort levels (off, low, medium, high, max). See the main repo for benchmarks and details.

Run it

# llama.cpp
llama-server -hf Mincofficial/Minico-M1-1105-GGUF:Q8_0 --jinja --chat-template-kwargs '{"reasoning_effort":"high"}'

# Ollama
ollama run hf.co/Mincofficial/Minico-M1-1105-GGUF:Q8_0

# LM Studio: search for "Mincofficial/Minico-M1-1105-GGUF"

Use --jinja with llama.cpp so the bundled chat template (with the effort levels) is used. With Ollama, pick the effort by sending a system message that is exactly Reasoning effort: low (or off, medium, high, max); without one it uses high.

Effort levels

The chat template also accepts aliases (none, minimal, xhigh, and others) and enable_thinking=False, which means off. Without a reasoning_effort, and for unknown values, it uses high (the default since 2026-11-08; it was medium). Recommended sampling: temperature 0.1–0.3, top_k 50, repetition penalty 1.05.

Pick one effort per conversation. Switching the effort, or turning thinking on or off, partway through a chat is not recommended: the model was trained on chats that keep one setting from start to finish. Start a new chat to change it.

License

Minico M1 1105 is a modified version of LiquidAI/LFM2.5-350M and is released under the LFM Open License v1.0 (see LICENSE). The weights were changed by fine-tuning (SFT, DPO, GRPO) and weight merging, as described above. Commercial use is allowed for organisations under the revenue threshold set in the license; read it before using the model commercially.

Built on LFM2.5-350M by Liquid AI. Attribution notices from the base model are kept in LICENSE.