Athene-V2 is a 72B parameter model which excels at code completion, mathematics, and log extraction tasks.

tools 72b

ollama run athene-v2

curl http://localhost:11434/api/chat \
  -d '{
    "model": "athene-v2",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='athene-v2',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'athene-v2',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code ollama launch claude --model athene-v2

Codex ollama launch codex --model athene-v2

OpenCode ollama launch opencode --model athene-v2

OpenClaw ollama launch openclaw --model athene-v2

Models

View all →

Name

17 models

Size

Context

Input

athene-v2:latest

47GB · 32K context window · Text · 1 year ago

athene-v2:latest

47GB

32K

Text

athene-v2:72b

latest

47GB · 32K context window · Text · 1 year ago

athene-v2:72b latest

47GB

32K

Text

Readme

Athene-V2

Nexusflow’s Athene-V2 chat model, built on Qwen 2.5’s 72B foundation, achieves GPT-4o-level performance across key benchmarks while demonstrating how targeted optimization can enhance specific capabilities beyond traditional scaling approaches.

Model Features

72B parameters fine-tuned from Qwen 2.5
State-of-the-art chat performance matching or exceeding GPT-4o
Superior code completion (ranking #2 on bigcode-bench-hard)
Enhanced mathematics capabilities (MATH benchmark)
Precise long-form log extraction
Advanced post-training pipeline pushing the Pareto frontier

References

Blog post

HuggingFace