bcluzel/ LFM2.5-1.2B-Instruct

423 Downloads Updated 2 months ago

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

tools

ollama run bcluzel/LFM2.5-1.2B-Instruct:Q4_K_M

curl http://localhost:11434/api/chat \
  -d '{
    "model": "bcluzel/LFM2.5-1.2B-Instruct:Q4_K_M",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='bcluzel/LFM2.5-1.2B-Instruct:Q4_K_M',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'bcluzel/LFM2.5-1.2B-Instruct:Q4_K_M',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code

Claude Code ollama launch claude --model bcluzel/LFM2.5-1.2B-Instruct:Q4_K_M

Codex App

Codex App ollama launch codex-app --model bcluzel/LFM2.5-1.2B-Instruct:Q4_K_M

OpenClaw

OpenClaw ollama launch openclaw --model bcluzel/LFM2.5-1.2B-Instruct:Q4_K_M

Hermes Agent

Hermes Agent ollama launch hermes --model bcluzel/LFM2.5-1.2B-Instruct:Q4_K_M

Codex

Codex ollama launch codex --model bcluzel/LFM2.5-1.2B-Instruct:Q4_K_M

OpenCode

OpenCode ollama launch opencode --model bcluzel/LFM2.5-1.2B-Instruct:Q4_K_M

Models

Name

2 models

Size / Usage

Context

Input

LFM2.5-1.2B-Instruct:Q4_K_M

731MB · 125K context window · Text · 2 months ago

LFM2.5-1.2B-Instruct:Q4_K_M

731MB

125K

Text

LFM2.5-1.2B-Instruct:Q8_0

1.2GB · 125K context window · Text · 2 months ago

LFM2.5-1.2B-Instruct:Q8_0

1.2GB

125K

Text

Readme

LFM2.5-1.2B-Instruct

Instruct model with strong tool calling capabilities.

https://huggingface.co/LiquidAI/LFM2.5-1.2B-Instruct