neolinschen/ llama-coding

45 Downloads Updated 2 weeks ago

Llama Coding with small Models

tools 1b 3b

ollama run neolinschen/llama-coding:1b

curl http://localhost:11434/api/chat \
  -d '{
    "model": "neolinschen/llama-coding:1b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='neolinschen/llama-coding:1b',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'neolinschen/llama-coding:1b',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code

Claude Code ollama launch claude --model neolinschen/llama-coding:1b

Codex App

Codex App ollama launch codex-app --model neolinschen/llama-coding:1b

OpenClaw

OpenClaw ollama launch openclaw --model neolinschen/llama-coding:1b

Hermes Agent

Hermes Agent ollama launch hermes --model neolinschen/llama-coding:1b

Codex

Codex ollama launch codex --model neolinschen/llama-coding:1b

OpenCode

OpenCode ollama launch opencode --model neolinschen/llama-coding:1b

Models

Name

2 models

Size / Usage

Context

Input

llama-coding:1b

1.3GB · 128K context window · Text · 2 weeks ago

llama-coding:1b

1.3GB

128K

Text

llama-coding:3b

2.0GB · 128K context window · Text · 2 weeks ago

llama-coding:3b

2.0GB

128K

Text

Readme

Llama Coding 🤖

A lightweight coding assistant based on Meta’s Llama 3.2, optimized for coding tasks and agent workflows.

Models

Tag	Size	Best for
`1b`	~1GB	Fast, low resources
`3b`	~2GB	Best quality

Usage

ollama run neolinschen/llama-coding:3b

What it can do

Write and debug code in any language
Explain code step by step
Help with agent tasks and automation
Answer coding questions concisely

Based on

Llama 3.2 by Meta