lfm2.5

LFM2.5-8B-A1B, an edge model built for fast, reliable tool calling on consumer hardware.

tools thinking 8b

173K Pulls 5 Tags Updated 4 months ago

lfm2.5-thinking

LFM2.5 is a new family of hybrid models designed for on-device deployment.

tools thinking 1.2b

1.3M Pulls 5 Tags Updated 8 months ago

richardyoung/lfm2.5-1.2b-instruct-heretic

Uncensored LFM2.5-1.2B-Instruct via Heretic: 3/100 refusals (from 98), KL 0.059. Tiny and fast; runs on almost anything.

61 Pulls 5 Tags Updated 3 days ago

ghunghab/lfm2.5-8b-a1b

2 Pulls 3 Tags Updated 3 days ago

LiquidAI/lfm2.5-2.6b

Fast 2.6B local AI agent with thinking that rivals models 4x larger on tool use and multi-step agentic tasks.

tools thinking

769 Pulls 8 Tags Updated 2 weeks ago

virtuanista/lfm2.5-8b-a1b-uncensored

Versión GGUF sin censura del modelo lfm2.5-8b-a1b de Liquid AI, lista para ejecutar en local.

208 Pulls 5 Tags Updated 2 weeks ago

LiquidAI-dev/lfm2.5-2.6b

tools thinking

61 Pulls 8 Tags Updated 2 weeks ago

LiquidAI-dev/lfm2.5-350m

tools

57 Pulls 8 Tags Updated 2 weeks ago

LiquidAI/lfm2.5-1.2b-instruct

Blazingly fast 1.2B local AI chat model for on-device conversations, RAG, and tool calling.

8,664 Pulls 6 Tags Updated 5 months ago

oamazonasgabriel/lfm2.5-2.6b

LFM2.5-2.6B by Liquid AI — deploy agents everywhere. A 2.6B dense reasoning model (Q4_K_M, ~1.7 GB) with native tool calling, 128K context, and 16-language support. Runs on any 8 GB GPU.

1,809 Pulls 1 Tag Updated 1 month ago

s1gnature/lfm2.5

tools thinking 1.2b 2.6b 8b

23 Pulls 3 Tags Updated 2 weeks ago

LiquidAI/lfm2.5-350m

Ultra-fast 350M local AI model for data extraction, structured output, and tool use.

2,494 Pulls 6 Tags Updated 5 months ago

maternion/lfm2.5

LFM2.5-350M & LFM2.5-8B-A1B are fast, memory-efficient hybrid MoE language models. Unsloth Dynamic (UD) quants available.

tools thinking 350m 8b

1,840 Pulls 15 Tags Updated 3 months ago

oamazonasgabriel/lfm2.5-230m

LFM2.5-230M is a hybrid language model by Liquid AI, Built to Run Anywhere. The ideal lightweight AI companion for: 4 GB laptops · 8 GB desktops · Edge devices · Raspberry Pi 5

447 Pulls 1 Tag Updated 3 weeks ago

batiai/lfm2.5-8b

284 Pulls 6 Tags Updated 3 months ago

pierreprudh/lfm2.5-8b-a1b

LFM2.5-8B-A1B Q8_0 with working tool calls — fixes the llama.cpp parser crash (#23838). Same weights, metadata-only fix.

tools thinking

241 Pulls 2 Tags Updated 3 months ago

oamazonasgabriel/lfm2.5-8b-a1b

A general-purpose 8.3B Mixture-of-Experts model from Liquid AI that activates only ~1.5B parameters per token — delivering strong reasoning, tool calling, and multilingual support while fitting comfortably in 8 GB VRAM.

143 Pulls 1 Tag Updated 2 months ago

jonathanbuchanan/lfm2.5-vl-450m

vision

206 Pulls 1 Tag Updated 5 months ago

jpmarindiaz/lfm2.5-vl-450m

https://huggingface.co/LiquidAI/LFM2.5-VL-450M

133 Pulls 1 Tag Updated 4 months ago

dhiltgen/lfm2.5-thinking

tools thinking

121 Pulls 6 Tags Updated 2 months ago