Instructions to use allura-org/Q3-30B-A3B-Designant with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use allura-org/Q3-30B-A3B-Designant with Transformers:

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

pipe = pipeline("text-generation", model="allura-org/Q3-30B-A3B-Designant")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("allura-org/Q3-30B-A3B-Designant")
model = AutoModelForCausalLM.from_pretrained("allura-org/Q3-30B-A3B-Designant", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use allura-org/Q3-30B-A3B-Designant with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "allura-org/Q3-30B-A3B-Designant"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "allura-org/Q3-30B-A3B-Designant",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/allura-org/Q3-30B-A3B-Designant

SGLang

How to use allura-org/Q3-30B-A3B-Designant 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 "allura-org/Q3-30B-A3B-Designant" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "allura-org/Q3-30B-A3B-Designant",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "allura-org/Q3-30B-A3B-Designant" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "allura-org/Q3-30B-A3B-Designant",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use allura-org/Q3-30B-A3B-Designant 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 allura-org/Q3-30B-A3B-Designant 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 allura-org/Q3-30B-A3B-Designant to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for allura-org/Q3-30B-A3B-Designant to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="allura-org/Q3-30B-A3B-Designant",
    max_seq_length=2048,
)

Docker Model Runner
How to use allura-org/Q3-30B-A3B-Designant with Docker Model Runner:
```
docker model run hf.co/allura-org/Q3-30B-A3B-Designant
```

Fizzarolli commited on May 27, 2025

Commit

f2fce2d

verified ·

1 Parent(s): a3a7f1a

Update README.md

Browse files

Files changed (1) hide show

README.md +9 -1

README.md CHANGED Viewed

@@ -42,6 +42,14 @@ During testing, Designant punched well above its weight class in terms of active
 # Quantizations
 EXL3:
 - [our EXL3 collection](https://huggingface.co/collections/allura-quants/q3-30b-a3b-designant-exl3-6834d8b8c9e9cbffba5cf265)
@@ -52,7 +60,7 @@ GGUF:
 - [imatrix GGUFs by Bartowski](https://huggingface.co/bartowski/allura-org_Q3-30B-A3B-Designant-GGUF)
 - [Linear GGUFs by mradermacher](https://huggingface.co/mradermacher/Q3-30B-A3B-Designant-GGUF)
-<sup>Some users report issues with low-bit GGUF quants for Qwen3 MoE models. We'd recommend trying both imatrix and linear, as well as q5+ for proper quality.</sup>
 # Usage

 # Quantizations
+<div style="background-color: #ff6961; padding: 10px 15px; display: flex; align-items: center; max-width: 100%; box-sizing: border-box; border-radius: 5px;">
+  <span style="color: yellow; font-size: 1.6em; margin-right: 10px; line-height: 1;">⚠️</span>
+  <span style="color: black; font-family: sans-serif; font-size: 1em;">
+    Warning: Quantization seems very janky with Qwen 3 MoE models. We recommend using full bf16 weights and vLLM, if possible.
+  </span>
+</div>
 EXL3:
 - [our EXL3 collection](https://huggingface.co/collections/allura-quants/q3-30b-a3b-designant-exl3-6834d8b8c9e9cbffba5cf265)
 - [imatrix GGUFs by Bartowski](https://huggingface.co/bartowski/allura-org_Q3-30B-A3B-Designant-GGUF)
 - [Linear GGUFs by mradermacher](https://huggingface.co/mradermacher/Q3-30B-A3B-Designant-GGUF)
+<sup>Some users report even more issues with low-bit GGUF quants for Qwen3 MoE models. We'd recommend trying both imatrix and linear, as well as q5+ for proper quality.</sup>
 # Usage