Instructions to use nphearum/Qwen3.5-4BxOpus-4.7-Code-Reasoning-Distilled-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nphearum/Qwen3.5-4BxOpus-4.7-Code-Reasoning-Distilled-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="nphearum/Qwen3.5-4BxOpus-4.7-Code-Reasoning-Distilled-GGUF",
	filename="Qwen3.5-4B.BF16-mmproj.gguf",
)

llm.create_chat_completion(
	messages = "{\n    \"question\": \"What is my name?\",\n    \"context\": \"My name is Clara and I live in Berkeley.\"\n}"
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use nphearum/Qwen3.5-4BxOpus-4.7-Code-Reasoning-Distilled-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf nphearum/Qwen3.5-4BxOpus-4.7-Code-Reasoning-Distilled-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf nphearum/Qwen3.5-4BxOpus-4.7-Code-Reasoning-Distilled-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 nphearum/Qwen3.5-4BxOpus-4.7-Code-Reasoning-Distilled-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf nphearum/Qwen3.5-4BxOpus-4.7-Code-Reasoning-Distilled-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 nphearum/Qwen3.5-4BxOpus-4.7-Code-Reasoning-Distilled-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf nphearum/Qwen3.5-4BxOpus-4.7-Code-Reasoning-Distilled-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 nphearum/Qwen3.5-4BxOpus-4.7-Code-Reasoning-Distilled-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf nphearum/Qwen3.5-4BxOpus-4.7-Code-Reasoning-Distilled-GGUF:Q4_K_M

Use Docker

docker model run hf.co/nphearum/Qwen3.5-4BxOpus-4.7-Code-Reasoning-Distilled-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use nphearum/Qwen3.5-4BxOpus-4.7-Code-Reasoning-Distilled-GGUF with Ollama:
```
ollama run hf.co/nphearum/Qwen3.5-4BxOpus-4.7-Code-Reasoning-Distilled-GGUF:Q4_K_M
```

Unsloth Studio new

How to use nphearum/Qwen3.5-4BxOpus-4.7-Code-Reasoning-Distilled-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 nphearum/Qwen3.5-4BxOpus-4.7-Code-Reasoning-Distilled-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 nphearum/Qwen3.5-4BxOpus-4.7-Code-Reasoning-Distilled-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for nphearum/Qwen3.5-4BxOpus-4.7-Code-Reasoning-Distilled-GGUF to start chatting

Pi new

How to use nphearum/Qwen3.5-4BxOpus-4.7-Code-Reasoning-Distilled-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf nphearum/Qwen3.5-4BxOpus-4.7-Code-Reasoning-Distilled-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Qwen3.5-4BxOpus-4.7-Code-Reasoning-Distilled-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use nphearum/Qwen3.5-4BxOpus-4.7-Code-Reasoning-Distilled-GGUF with Docker Model Runner:
```
docker model run hf.co/nphearum/Qwen3.5-4BxOpus-4.7-Code-Reasoning-Distilled-GGUF:Q4_K_M
```

Lemonade

How to use nphearum/Qwen3.5-4BxOpus-4.7-Code-Reasoning-Distilled-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull nphearum/Qwen3.5-4BxOpus-4.7-Code-Reasoning-Distilled-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.5-4BxOpus-4.7-Code-Reasoning-Distilled-GGUF-Q4_K_M

List all available models

lemonade list

Qwen3.5-4BxOpus-4.7-Code-Reasoning-Distilled-GGUF

A distilled 4B code/reasoning model in GGUF format, optimized for local inference via llama.cpp.

Quick Start

llama-cli -hf nphearum/Qwen3.5-4BxOpus-4.7-Code-Reasoning-Distilled-GGUF --jinja

Server Launch

llama-server \
  -m Qwen3.5-4BxOpus-4.7-Code-Reasoning-Distilled.Q4_K_M.gguf \
  --port 8001 --alias qwen3.5-4b-opus \
  -c 65536 -n 8192 \
  --temp 0.6 --top-p 0.95 --top-k 40 --repeat-penalty 1.05 \
  --flash-attn on --ctk q8_0 --ctv q8_0 \
  --jinja --chat-template-kwargs '{"enable_thinking": true}' \
  -ngl -1

Preset Configs

Mode	Flags
Coding	`--temp 0.4 --top-p 0.9 --top-k 50 --repeat-penalty 1.1`
Reasoning	`--temp 0.6 --top-p 0.95 --top-k 40`
Low VRAM	`-c 32768 -n 4096 --flash-attn off -ngl 20`

Key Specs

Base: Qwen3.5 4B · Format: Q4_K_M GGUF
Context: 32K–64K practical · Output: up to 8K tokens
KV cache: 8-bit (q8_0) · GPU: full offload (-ngl -1)
Thinking mode: optional — improves reasoning, adds latency

Caveats

Quality drops beyond 64K context
4B class — sensitive to sampling parameters
Thinking mode can produce unstable output if misaligned with training

Downloads last month: 1,052

GGUF

Model size

4B params

Architecture

qwen35

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for nphearum/Qwen3.5-4BxOpus-4.7-Code-Reasoning-Distilled-GGUF

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Quantized

(171)

this model

Datasets used to train nphearum/Qwen3.5-4BxOpus-4.7-Code-Reasoning-Distilled-GGUF

Collection including nphearum/Qwen3.5-4BxOpus-4.7-Code-Reasoning-Distilled-GGUF

Qwen Vers

Collection

3 items • Updated 1 day ago