An uncensored model derived from Mistral-Nemo (12b). It ranks top 3 on the UGI leaderboard for models of its size. It was created by "Yamata Zen" and quantized by "team mradermacher".

tools

ollama run MartinRizzo/Ayla-Light-v2:12b-q4_K_M

curl http://localhost:11434/api/chat \
  -d '{
    "model": "MartinRizzo/Ayla-Light-v2:12b-q4_K_M",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='MartinRizzo/Ayla-Light-v2:12b-q4_K_M',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'MartinRizzo/Ayla-Light-v2:12b-q4_K_M',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code ollama launch claude --model MartinRizzo/Ayla-Light-v2:12b-q4_K_M

Codex ollama launch codex --model MartinRizzo/Ayla-Light-v2:12b-q4_K_M

OpenCode ollama launch opencode --model MartinRizzo/Ayla-Light-v2:12b-q4_K_M

OpenClaw ollama launch openclaw --model MartinRizzo/Ayla-Light-v2:12b-q4_K_M

Models

View all →

Name

1 model

Size

Context

Input

Ayla-Light-v2:12b-q4_K_M

7.5GB · 1000K context window · Text · 1 year ago

Ayla-Light-v2:12b-q4_K_M

7.5GB

1000K

Text

Readme

Ayla-Light-v2

This model was developed by Yamata Zen and ranks among the top 3 on the UGI leaderboard for models with 12 billion parameters or less. It is an uncensored version of mistral-nemo that demonstrates excellent performance.

Reference

HuggingFace Model Card

GGUF Quants by mradermacher