Instructions to use constructai/Qwenite3.5-2B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use constructai/Qwenite3.5-2B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="constructai/Qwenite3.5-2B-GGUF",
	filename="Qwenite3.5-2B-F16.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 constructai/Qwenite3.5-2B-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf constructai/Qwenite3.5-2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf constructai/Qwenite3.5-2B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf constructai/Qwenite3.5-2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf constructai/Qwenite3.5-2B-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 constructai/Qwenite3.5-2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf constructai/Qwenite3.5-2B-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 constructai/Qwenite3.5-2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf constructai/Qwenite3.5-2B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/constructai/Qwenite3.5-2B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use constructai/Qwenite3.5-2B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "constructai/Qwenite3.5-2B-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "constructai/Qwenite3.5-2B-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/constructai/Qwenite3.5-2B-GGUF:Q4_K_M

Ollama
How to use constructai/Qwenite3.5-2B-GGUF with Ollama:
```
ollama run hf.co/constructai/Qwenite3.5-2B-GGUF:Q4_K_M
```

Unsloth Studio

How to use constructai/Qwenite3.5-2B-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 constructai/Qwenite3.5-2B-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 constructai/Qwenite3.5-2B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for constructai/Qwenite3.5-2B-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use constructai/Qwenite3.5-2B-GGUF with Docker Model Runner:
```
docker model run hf.co/constructai/Qwenite3.5-2B-GGUF:Q4_K_M
```

Lemonade

How to use constructai/Qwenite3.5-2B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull constructai/Qwenite3.5-2B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwenite3.5-2B-GGUF-Q4_K_M

List all available models

lemonade list

💥 Qwenite3.5-2B-GGUF

📄 Overview


Base Model	constructai/Qwenite3.5-2B
Parameters	2B

Quant types

Quant type	Size
Q2_K	0.90 GB
Q3_K_S	0.95 GB
Q3_K_M	1.02 GB
Q3_K_L	1.08 GB
IQ4_XS	1.12 GB
Q4_K_S	1.13 GB
Q4_K_M	1.19 GB
Q5_K_S	1.28 GB
Q5_K_M	1.31 GB
Q6_K	1.45 GB
Q8_0	1.87 GB
F16	3.78 GB

🎯 Intended Use

This model is designed for step‑by‑step reasoning tasks where the answer requires logical decomposition before the final response. It is optimized for:

Educational applications — explaining "why" and "how" questions
On‑device assistants — runs on mobile, Raspberry Pi, or CPU‑only environments in q4_k_m
Reasoning distillation research — studying how small models learn from large ones (Granite → Qwen)

Not recommended for: multimodal tasks, non‑reasoning chat (e.g., creative writing), or production systems requiring 100% factual accuracy.

⚠️ Limitations & Intended Use

Intended Use:

Educational & Reasoning tasks — explaining step‑by‑step logic (math, science, common sense)
On‑device assistants — runs on CPU, Raspberry Pi, mobile (small footprint, fast inference) in q4_k_m
Research baseline — for studying SFT‑only reasoning without RLHF/DPO
Distillation experiments — testing how well small models learn from large (Granite → Qwen)

Limitations:

Size matters — 2B parameters, so complex or multi‑hop reasoning may still fail
No multimodal — text only; images, video, audio are not supported
Factual accuracy — may hallucinate or give incorrect answers; always verify critical outputs
Domain restricted — trained on 15,000 reasoning examples (2 epochs); general chat or creative writing may be suboptimal
Training data bias — inherits biases from constructai/Granite-v4.1-Distilled-15K dataset; not safety‑filtered for harmful content
Hardware specific — optimised for T4/consumer GPUs; very slow on CPU without quantisation

🙏 Acknowledgements

This project would not have been possible without the open‑source community and the following resources:

Qwen Team (Alibaba Cloud) — for releasing the Qwen3.5-0.8B-Base model under Apache 2.0, a perfect balance of size and intelligence.
Unsloth AI — for making fine‑tuning on consumer hardware fast and memory‑efficient.
Hugging Face — for the ecosystem (transformers, datasets, PEFT, Hub) that democratises LLM training.
Kaggle — for providing free T4 GPU runtime to run this experiment.

📖 Citation

@misc{Qwenite3.5-2B-GGUF,
  author = {constructai},
  title = {Qwenite3.5-2B: Small Reasoning Model via SFT on Granite Traces},
  year = {2026},
  publisher = {Hugging Face},
  howpublished = {https://huggingface.co/constructai/Qwenite3.5-2B-GGUF},
}

Downloads last month: 60

GGUF

Model size

2B params

Architecture

qwen35

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for constructai/Qwenite3.5-2B-GGUF

Base model

constructai/Qwenite3.5-2B

Quantized

(1)

this model

Collection including constructai/Qwenite3.5-2B-GGUF

Qwenite

Collection

4 items • Updated May 4