Based on Qwen3.5-122B-A10B and converted from the MLX Community 4-bit release (https://huggingface.co/mlx-community/Qwen3.5-122B-A10B-4bit)

vision tools thinking

ollama run rekiniasty/qwen3.5:122b-a10b-mlx-int4

curl http://localhost:11434/api/chat \
  -d '{
    "model": "rekiniasty/qwen3.5:122b-a10b-mlx-int4",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='rekiniasty/qwen3.5:122b-a10b-mlx-int4',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'rekiniasty/qwen3.5:122b-a10b-mlx-int4',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code ollama launch claude --model rekiniasty/qwen3.5:122b-a10b-mlx-int4

Codex App ollama launch codex-app --model rekiniasty/qwen3.5:122b-a10b-mlx-int4

OpenClaw ollama launch openclaw --model rekiniasty/qwen3.5:122b-a10b-mlx-int4

Hermes Agent ollama launch hermes --model rekiniasty/qwen3.5:122b-a10b-mlx-int4

Codex ollama launch codex --model rekiniasty/qwen3.5:122b-a10b-mlx-int4

OpenCode ollama launch opencode --model rekiniasty/qwen3.5:122b-a10b-mlx-int4

Models

View all →

Name

1 model

Size / Usage

Context

Input

qwen3.5:122b-a10b-mlx-int4

MLX

70GB · 256K context window · Text, Image · 1 week ago

qwen3.5:122b-a10b-mlx-int4 MLX

70GB

256K

Text, Image

Readme

Qwen3.5 122B A10B 4bit

Qwen3.5-122B-A10B quantized to 4-bit for efficient local deployment. Delivers strong reasoning, coding, and multilingual capabilities while significantly reducing memory requirements.

Source

Based on Qwen3.5-122B-A10B and converted from the MLX Community 4-bit release. https://huggingface.co/mlx-community/Qwen3.5-122B-A10B-4bit