Instructions to use AlexanderKyng/Qwopus-27B-Coder-Mixed-Q5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AlexanderKyng/Qwopus-27B-Coder-Mixed-Q5 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="AlexanderKyng/Qwopus-27B-Coder-Mixed-Q5")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("AlexanderKyng/Qwopus-27B-Coder-Mixed-Q5", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AlexanderKyng/Qwopus-27B-Coder-Mixed-Q5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AlexanderKyng/Qwopus-27B-Coder-Mixed-Q5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AlexanderKyng/Qwopus-27B-Coder-Mixed-Q5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/AlexanderKyng/Qwopus-27B-Coder-Mixed-Q5

SGLang

How to use AlexanderKyng/Qwopus-27B-Coder-Mixed-Q5 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 "AlexanderKyng/Qwopus-27B-Coder-Mixed-Q5" \
    --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": "AlexanderKyng/Qwopus-27B-Coder-Mixed-Q5",
		"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 "AlexanderKyng/Qwopus-27B-Coder-Mixed-Q5" \
        --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": "AlexanderKyng/Qwopus-27B-Coder-Mixed-Q5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio

How to use AlexanderKyng/Qwopus-27B-Coder-Mixed-Q5 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 AlexanderKyng/Qwopus-27B-Coder-Mixed-Q5 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 AlexanderKyng/Qwopus-27B-Coder-Mixed-Q5 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for AlexanderKyng/Qwopus-27B-Coder-Mixed-Q5 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="AlexanderKyng/Qwopus-27B-Coder-Mixed-Q5",
    max_seq_length=2048,
)

Docker Model Runner
How to use AlexanderKyng/Qwopus-27B-Coder-Mixed-Q5 with Docker Model Runner:
```
docker model run hf.co/AlexanderKyng/Qwopus-27B-Coder-Mixed-Q5
```

great quant!!

by pawarshardul - opened 6 days ago

Discussion

pawarshardul

6 days ago

•

edited 6 days ago

thank you for awesome quant -- i got 68-70 t/s speed on my 2x 3090 setup with full context !!
i recently noticed https://huggingface.co/migtissera/Tess-4-27B this fintune of qwen -- supposted to be better than qwopus -- can you make mixed quant like this for that or if you can create a guide to do that would be nice too !!

AlexanderKyng

Owner 5 days ago

First, thank you for your feedback, I am very please to know my work is useful !
Thank you also for this fine-tune, which I never heard about. I am currently working on Agents-A1 (fine tuned from Qwen3.5-35B-A3B) and this one will come next. I suppose that I should be able to publish it at the beginning of the next week, it is downloading right now.

I didn't think of writing a guide but that is a very good idea. I learned so much from these quants, I think it can be of good value for many in the community !

AlexanderKyng

Owner 3 days ago

Hi again Pawarshardul,

It's finally uploaded and I hope it meets your needs !

https://huggingface.co/AlexanderKyng/Tess-4-27B-Mixed-Q5

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment