Instructions to use constructai/Qweling3.5-0.8B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use constructai/Qweling3.5-0.8B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="constructai/Qweling3.5-0.8B-GGUF",
	filename="Qweling3.5-0.8B-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/Qweling3.5-0.8B-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/Qweling3.5-0.8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf constructai/Qweling3.5-0.8B-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/Qweling3.5-0.8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf constructai/Qweling3.5-0.8B-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/Qweling3.5-0.8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf constructai/Qweling3.5-0.8B-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/Qweling3.5-0.8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf constructai/Qweling3.5-0.8B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/constructai/Qweling3.5-0.8B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use constructai/Qweling3.5-0.8B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "constructai/Qweling3.5-0.8B-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/Qweling3.5-0.8B-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/constructai/Qweling3.5-0.8B-GGUF:Q4_K_M

Ollama
How to use constructai/Qweling3.5-0.8B-GGUF with Ollama:
```
ollama run hf.co/constructai/Qweling3.5-0.8B-GGUF:Q4_K_M
```

Unsloth Studio

How to use constructai/Qweling3.5-0.8B-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/Qweling3.5-0.8B-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/Qweling3.5-0.8B-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/Qweling3.5-0.8B-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use constructai/Qweling3.5-0.8B-GGUF with Docker Model Runner:
```
docker model run hf.co/constructai/Qweling3.5-0.8B-GGUF:Q4_K_M
```

Lemonade

How to use constructai/Qweling3.5-0.8B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull constructai/Qweling3.5-0.8B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qweling3.5-0.8B-GGUF-Q4_K_M

List all available models

lemonade list

constructai commited on May 3

Commit

14ad03d

verified ·

1 Parent(s): bd18150

Update README.md

Browse files

Files changed (1) hide show

README.md +21 -9

README.md CHANGED Viewed

@@ -3,8 +3,8 @@ license: apache-2.0
 pipeline_tag: text-generation
 tags:
 - unsloth
-datasets:
-- constructai/Ling-v2.6-Flash-Distilled-15K
 ---
 # 💥 Qweling3.5-0.8B-GGUF
@@ -15,13 +15,25 @@ datasets:
 | | |
 |---|---|
-| **Model Name** | constructai/Qweling3.5-0.8B |
-| **Base Model** | Qwen3.5-0.8B-Base |
-| **Dataset** | constructai/Ling-v2.6-Flash-Distilled-15K |
-| **Training Type** | Supervised Fine-Tuning (SFT) |
 | **Parameters** | 0.9B |
-| **Framework** | Unsloth + LoRA |
-| **Hardware** | NVIDIA T4 16GB |
 ---
@@ -85,7 +97,7 @@ This project would not have been possible without the open‑source community an
 ```bibtex
 @misc{Qweling3.5-0.8B-GGUF,
   author = {constructai},
-  title = {Qwenling3.5-0.8B-GGUF: Small Reasoning Model via SFT on Ling Traces},
   year = {2026},
   publisher = {Hugging Face},
   howpublished = {https://huggingface.co/constructai/Qweling3.5-0.8B-GGUF},

 pipeline_tag: text-generation
 tags:
 - unsloth
+base_model:
+- constructai/Qweling3.5-0.8B
 ---
 # 💥 Qweling3.5-0.8B-GGUF
 | | |
 |---|---|
+| **Base Model** | constructai/QwenGLM3.5-0.8B |
 | **Parameters** | 0.9B |
+**Quant types**
+| Quant type | Size |
+|---|---|
+| **Q2_K** | 422 MB |
+| **Q3_K_S** | 435 MB |
+| **Q3_K_M** | 466 MB |
+| **Q3_K_L** | 491 MB |
+| **IQ4_XS** | 506 MB |
+| **Q4_K_S** | 505 MB |
+| **Q4_K_M** | 529 MB |
+| **Q5_K_S** | 564 MB |
+| **Q5_K_M** | 578 MB |
+| **Q6_K** | 630 MB |
+| **Q8_0** | 812 MB |
+| **F16** | 1.52 GB |
 ---
 ```bibtex
 @misc{Qweling3.5-0.8B-GGUF,
   author = {constructai},
+  title = {Qwenling3.5-0.8B: Small Reasoning Model via SFT on Ling Traces},
   year = {2026},
   publisher = {Hugging Face},
   howpublished = {https://huggingface.co/constructai/Qweling3.5-0.8B-GGUF},