ornith:35b-q8

ornith:35b-q8_0

3,176 Downloads Updated 13 hours ago

A self-improving family of open-source models for agentic coding

9b 35b

ollama run ornith:35b-q8_0

curl http://localhost:11434/api/chat \
  -d '{
    "model": "ornith:35b-q8_0",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='ornith:35b-q8_0',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'ornith:35b-q8_0',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 14 hours ago

14 hours ago

44788b2fdab4 · 37GB ·

model

archqwen35moe

parameters34.7B

quantizationQ8_0

37GB

system

You are Ornith, an open-source agentic coding assistant. Think step by step in a reasoning block, th

236B

license

MIT License Copyright (c) [year] [fullname] Permission is hereby granted, free of charge, to any per

1.1kB

params

{ "stop": [ "<|im_end|>" ], "temperature": 0.6, "top_k": 20, "top_p": 0.

76B

Readme

Highlights:

State-of-the-Art Coding Agents: Achieving state-of-the-art performance among open-source models of comparable size on coding benchmarks such as Terminal-Bench 2.1, SWE-Bench, NL2Repo and OpenClaw.
Self-Improving Training Framework: Ornith-1.0 employs RL to learn to generate not only solution rollouts, but also the scallfold that drive those rollouts. By jointly optimizing the scaffold and the resulting solution, the model discovers better search trajectories and generates higher-quality solutions.
Licence: MIT licensed, globally accessible, and free from regional limitations.

9B

ollama run ornith:9b

35B

ollama run ornith:35b

References

Blog