Instructions to use brunopio/Qwen3.5-14B-A3B-Claude-4.6-Opus-Reasoning-Distilled-reap-Q4_K_M-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use brunopio/Qwen3.5-14B-A3B-Claude-4.6-Opus-Reasoning-Distilled-reap-Q4_K_M-GGUF with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="brunopio/Qwen3.5-14B-A3B-Claude-4.6-Opus-Reasoning-Distilled-reap-Q4_K_M-GGUF")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("brunopio/Qwen3.5-14B-A3B-Claude-4.6-Opus-Reasoning-Distilled-reap-Q4_K_M-GGUF", dtype="auto") - llama-cpp-python
How to use brunopio/Qwen3.5-14B-A3B-Claude-4.6-Opus-Reasoning-Distilled-reap-Q4_K_M-GGUF with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="brunopio/Qwen3.5-14B-A3B-Claude-4.6-Opus-Reasoning-Distilled-reap-Q4_K_M-GGUF", filename="qwen3.5-14b-a3b-claude-4.6-opus-reasoning-distilled-reap-q4_k_m.gguf", )
output = llm( "Once upon a time,", max_tokens=512, echo=True ) print(output)
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use brunopio/Qwen3.5-14B-A3B-Claude-4.6-Opus-Reasoning-Distilled-reap-Q4_K_M-GGUF with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf brunopio/Qwen3.5-14B-A3B-Claude-4.6-Opus-Reasoning-Distilled-reap-Q4_K_M-GGUF:Q4_K_M # Run inference directly in the terminal: llama-cli -hf brunopio/Qwen3.5-14B-A3B-Claude-4.6-Opus-Reasoning-Distilled-reap-Q4_K_M-GGUF:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf brunopio/Qwen3.5-14B-A3B-Claude-4.6-Opus-Reasoning-Distilled-reap-Q4_K_M-GGUF:Q4_K_M # Run inference directly in the terminal: llama-cli -hf brunopio/Qwen3.5-14B-A3B-Claude-4.6-Opus-Reasoning-Distilled-reap-Q4_K_M-GGUF:Q4_K_M
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf brunopio/Qwen3.5-14B-A3B-Claude-4.6-Opus-Reasoning-Distilled-reap-Q4_K_M-GGUF:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf brunopio/Qwen3.5-14B-A3B-Claude-4.6-Opus-Reasoning-Distilled-reap-Q4_K_M-GGUF:Q4_K_M
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf brunopio/Qwen3.5-14B-A3B-Claude-4.6-Opus-Reasoning-Distilled-reap-Q4_K_M-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf brunopio/Qwen3.5-14B-A3B-Claude-4.6-Opus-Reasoning-Distilled-reap-Q4_K_M-GGUF:Q4_K_M
Use Docker
docker model run hf.co/brunopio/Qwen3.5-14B-A3B-Claude-4.6-Opus-Reasoning-Distilled-reap-Q4_K_M-GGUF:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use brunopio/Qwen3.5-14B-A3B-Claude-4.6-Opus-Reasoning-Distilled-reap-Q4_K_M-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "brunopio/Qwen3.5-14B-A3B-Claude-4.6-Opus-Reasoning-Distilled-reap-Q4_K_M-GGUF" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "brunopio/Qwen3.5-14B-A3B-Claude-4.6-Opus-Reasoning-Distilled-reap-Q4_K_M-GGUF", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/brunopio/Qwen3.5-14B-A3B-Claude-4.6-Opus-Reasoning-Distilled-reap-Q4_K_M-GGUF:Q4_K_M
- SGLang
How to use brunopio/Qwen3.5-14B-A3B-Claude-4.6-Opus-Reasoning-Distilled-reap-Q4_K_M-GGUF with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "brunopio/Qwen3.5-14B-A3B-Claude-4.6-Opus-Reasoning-Distilled-reap-Q4_K_M-GGUF" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "brunopio/Qwen3.5-14B-A3B-Claude-4.6-Opus-Reasoning-Distilled-reap-Q4_K_M-GGUF", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "brunopio/Qwen3.5-14B-A3B-Claude-4.6-Opus-Reasoning-Distilled-reap-Q4_K_M-GGUF" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "brunopio/Qwen3.5-14B-A3B-Claude-4.6-Opus-Reasoning-Distilled-reap-Q4_K_M-GGUF", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Ollama
How to use brunopio/Qwen3.5-14B-A3B-Claude-4.6-Opus-Reasoning-Distilled-reap-Q4_K_M-GGUF with Ollama:
ollama run hf.co/brunopio/Qwen3.5-14B-A3B-Claude-4.6-Opus-Reasoning-Distilled-reap-Q4_K_M-GGUF:Q4_K_M
- Unsloth Studio
How to use brunopio/Qwen3.5-14B-A3B-Claude-4.6-Opus-Reasoning-Distilled-reap-Q4_K_M-GGUF with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for brunopio/Qwen3.5-14B-A3B-Claude-4.6-Opus-Reasoning-Distilled-reap-Q4_K_M-GGUF to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for brunopio/Qwen3.5-14B-A3B-Claude-4.6-Opus-Reasoning-Distilled-reap-Q4_K_M-GGUF to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for brunopio/Qwen3.5-14B-A3B-Claude-4.6-Opus-Reasoning-Distilled-reap-Q4_K_M-GGUF to start chatting
- Atomic Chat new
- Docker Model Runner
How to use brunopio/Qwen3.5-14B-A3B-Claude-4.6-Opus-Reasoning-Distilled-reap-Q4_K_M-GGUF with Docker Model Runner:
docker model run hf.co/brunopio/Qwen3.5-14B-A3B-Claude-4.6-Opus-Reasoning-Distilled-reap-Q4_K_M-GGUF:Q4_K_M
- Lemonade
How to use brunopio/Qwen3.5-14B-A3B-Claude-4.6-Opus-Reasoning-Distilled-reap-Q4_K_M-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull brunopio/Qwen3.5-14B-A3B-Claude-4.6-Opus-Reasoning-Distilled-reap-Q4_K_M-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.Qwen3.5-14B-A3B-Claude-4.6-Opus-Reasoning-Distilled-reap-Q4_K_M-GGUF-Q4_K_M
List all available models
lemonade list
Update metadata (general.languages, qwen35moe.rope.freq_base)
Updated metadata:
- general.languages: [zh, en, ko, ru]
- qwen35moe.rope.freq_base: 50000000
- tokenizer.chat_template:
{%- if tools %}
{{- '<|im_start|>system\n' }}
{%- if messages[0].role == 'system' %}
{{- messages[0].content + '\n\n' }}
{%- endif %}
{{- "You are a coding assistant that PRIORITIZES TOOL USE.
## CRITICAL RULES (MUST FOLLOW)
1. For ANY task that can use a tool → CALL TOOL IMMEDIATELY
2. NO thinking aloud, NO explanations before tool calls
3. NO conversational filler (\"Let me...\", \"I'll...\", \"Sure...\")
4. Output ONLY the tool call, nothing else
5. After tool response → evaluate → call next tool directly
6. Only use natural language if NO tool exists for the task
## AVAILABLE TOOLS
<tools>" }}
{%- for tool in tools %}
{{- '\n' }}
{{- tool | tojson }}
{%- endfor %}
{{- "\n</tools>
## TOOL CALL FORMAT (NO extra text)
<tool_call>
{\"name\": \"tool_name\", \"arguments\": {...}}
</tool_call>
## EXAMPLES
User: Read src/main.py
Assistant:
<tool_call>
{\"name\": \"read_file\", \"arguments\": {\"path\": \"src/main.py\"}}
</tool_call>
User: Find all .py files in src/
Assistant:
<tool_call>
{\"name\": \"file_glob_search\", \"arguments\": {\"pattern\": \"src/**/*.py\"}}
</tool_call>
User: Search for 'TODO' in codebase
Assistant:
<tool_call>
{\"name\": \"grep_search\", \"arguments\": {\"pattern\": \"TODO\", \"path\": \".\"}}
</tool_call>
User: Run ls -la
Assistant:
<tool_call>
{\"name\": \"exec_shell_command\", \"arguments\": {\"command\": \"ls -la\"}}
</tool_call>
User: Write to config.json
Assistant:
<tool_call>
{\"name\": \"write_file\", \"arguments\": {\"path\": \"config.json\", \"content\": \"{}\"}}
</tool_call>
User: Edit line 15
Assistant:
<tool_call>
{\"name\": \"edit_file\", \"arguments\": {\"path\": \"file.txt\", \"line\": 15, \"new_content\": \"updated\"}}
</tool_call>
User: Apply git diff
Assistant:
<tool_call>
{\"name\": \"apply_diff\", \"arguments\": {\"diff\": \"--- a/file\\n+++ b/file\\n@@ -1 +1 @@\\n-old\\n+new\"}}
</tool_call>
User: What time is it?
Assistant:
<tool_call>
{\"name\": \"get_datetime\", \"arguments\": {}}
</tool_call>
<|im_end|>\n" }}
{%- else %}
{%- if messages[0].role == 'system' %}
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- for message in messages %}
{%- if message.content is string %}
{%- set content = message.content %}
{%- else %}
{%- set content = '' %}
{%- endif %}
{%- if message.role == "user" %}
{{- '<|im_start|>user\n' + content + '<|im_end|>\n' }}
{%- elif message.role == "system" and not loop.first %}
{{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
{%- elif message.role == "assistant" %}
{{- '<|im_start|>assistant\n' }}
{%- if message.tool_calls %}
{%- for tool_call in message.tool_calls %}
{%- if tool_call.function %}
{%- set tool_call = tool_call.function %}
{%- endif %}
{%- if loop.first and content %}
{{- content + '\n' }}
{%- endif %}
<tool_call>
{"name": "{{ tool_call.name }}", "arguments": {{ tool_call.arguments | tojson if tool_call.arguments is mapping else tool_call.arguments }}}
</tool_call>
{%- if not loop.last %}{{ '\n' }}{% endif %}
{%- endfor %}
{%- else %}
{{- content }}
{%- endif %}
{{- '<|im_end|>\n' }}
{%- elif message.role == "tool" %}
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
{{- '<|im_start|>user' }}
{%- endif %}
{{- '\n<tool_response>\n' }}
{{- content }}
{{- '\n</tool_response>' }}
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
{{- '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|im_start|>assistant\n' }}
{%- endif %}