Llama Coding with small Models

tools 1b 3b

ollama run neolinschen/llama-coding:3b

curl http://localhost:11434/api/chat \
  -d '{
    "model": "neolinschen/llama-coding:3b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='neolinschen/llama-coding:3b',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'neolinschen/llama-coding:3b',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 2 weeks ago

2 weeks ago

ce2e56dd16ed · 2.0GB ·

model

archllama

parameters3.21B

quantizationQ4_K_M

2.0GB

template

<|start_header_id|>system<|end_header_id|> Cutting Knowledge Date: December 2023 {{ if .System }}{{

1.4kB

license

LLAMA 3.2 COMMUNITY LICENSE AGREEMENT Llama 3.2 Version Release Date: September 25, 2024 “Agreemen

7.7kB

license

**Llama 3.2** **Acceptable Use Policy** Meta is committed to promoting safe and fair use of its tool

6.0kB

system

You are a helpful coding assistant. Help the user with coding questions and agent tasks. Be concise

112B

params

{ "stop": [ "<|start_header_id|>", "<|end_header_id|>", "<|eot_id|>"

96B

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