fredrezones55/Qwen3.5-APEX

fredrezones55/ Qwen3.5-APEX

542 Downloads Updated 1 month ago

Qwen3.5-35B-A3B APEX GGUF -- A Novel MoE-Aware Mixed-Precision Quantization Technique Brought to you by the LocalAI team -- the creators of LocalAI the open-source AI engine that runs any model - LLMs, vision, image - on any hardware.

vision tools thinking

ollama run fredrezones55/Qwen3.5-APEX

curl http://localhost:11434/api/chat \
  -d '{
    "model": "fredrezones55/Qwen3.5-APEX",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='fredrezones55/Qwen3.5-APEX',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'fredrezones55/Qwen3.5-APEX',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code ollama launch claude --model fredrezones55/Qwen3.5-APEX

OpenClaw ollama launch openclaw --model fredrezones55/Qwen3.5-APEX

Hermes Agent ollama launch hermes --model fredrezones55/Qwen3.5-APEX

Codex ollama launch codex --model fredrezones55/Qwen3.5-APEX

OpenCode ollama launch opencode --model fredrezones55/Qwen3.5-APEX

Models

View all →

Name

2 models

Size / Usage

Context

Input

Qwen3.5-APEX:latest

14GB · 256K context window · Text, Image · 1 month ago

Qwen3.5-APEX:latest

14GB

256K

Text, Image

Qwen3.5-APEX:mini

latest

14GB · 256K context window · Text, Image · 1 month ago

Qwen3.5-APEX:mini latest

14GB

256K

Text, Image

Readme

Optimized Qwen3.5:35B MoE model with full vision support with GGUF based model.

My pipeline needed qwen35moe patching, but gguf model blob is fully functioning with vision and tooling. Ollama will not stop finetunes from showing their full potential.