doomgrave/cogito

doomgrave/ cogito

84 Downloads Updated 11 months ago

cogito:8b v1 Preview, quantized to Q2_K and Q3_K_S for GPU with 4gb Vram or less.

tools

ollama run doomgrave/cogito

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

from ollama import chat

response = chat(
    model='doomgrave/cogito',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

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

Applications

Claude Code ollama launch claude --model doomgrave/cogito

Codex ollama launch codex --model doomgrave/cogito

OpenCode ollama launch opencode --model doomgrave/cogito

OpenClaw ollama launch openclaw --model doomgrave/cogito

Models

View all →

Name

3 models

Size

Context

Input

cogito:latest

3.7GB · 128K context window · Text · 11 months ago

cogito:latest

3.7GB

128K

Text

cogito:cogito-Q2_K

3.2GB · 128K context window · Text · 11 months ago

cogito:cogito-Q2_K

3.2GB

128K

Text

cogito:cogito-Q3_K_S

3.7GB · 128K context window · Text · 11 months ago

cogito:cogito-Q3_K_S

3.7GB

128K

Text

Readme

No readme