Instructions to use MoLA-LLM/MoLA-v0.6-9x4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MoLA-LLM/MoLA-v0.6-9x4b with Transformers:

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

pipe = pipeline("text-generation", model="MoLA-LLM/MoLA-v0.6-9x4b", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("MoLA-LLM/MoLA-v0.6-9x4b", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use MoLA-LLM/MoLA-v0.6-9x4b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MoLA-LLM/MoLA-v0.6-9x4b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MoLA-LLM/MoLA-v0.6-9x4b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MoLA-LLM/MoLA-v0.6-9x4b

SGLang

How to use MoLA-LLM/MoLA-v0.6-9x4b 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 "MoLA-LLM/MoLA-v0.6-9x4b" \
    --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": "MoLA-LLM/MoLA-v0.6-9x4b",
		"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 "MoLA-LLM/MoLA-v0.6-9x4b" \
        --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": "MoLA-LLM/MoLA-v0.6-9x4b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MoLA-LLM/MoLA-v0.6-9x4b with Docker Model Runner:
```
docker model run hf.co/MoLA-LLM/MoLA-v0.6-9x4b
```

MoLA-LM: Mixture of LoRA Adapters LLM

MoLA-LM combines multiple LoRA adapters with an intelligent router to automatically select the best adapter for each input prompt. This approach enables specialized performance across different tasks while maintaining efficiency.

Important Note: The v0.5 had issues with the lora applying part of the custom lm class and its router was a bit too small with little generalization. In v0.6 and future models, all of these issues are/will be resolved.

TLDR: Dont use v0.5, use v0.6 and above.

Model Details

Model Type: Mixture of LoRA Adapters Language Model
Base Model: Qwen/Qwen3-4B-Thinking-2507
Total Adapters: 9
Architecture: Custom MoLAForCausalLM with automatic adapter routing

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
# Load the model (trust_remote_code=True is required for custom architecture)
model = AutoModelForCausalLM.from_pretrained(
    "MoLA-LLM/MoLA-v0.6-9x4b", 
    trust_remote_code=True, 
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("MoLA-LLM/MoLA-v0.6-9x4b", trust_remote_code=True)
# Use like any other language model - adapter selection is automatic
prompt = "Write a Python function to calculate fibonacci numbers"
messages = [{"role": "user", "content": prompt}]
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=8192, temperature=.6, do_sample=True)
response = tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True)
print(f"Selected LoRA: {model.get_current_lora()}")
print(response)

You can also use load_in_4bit and load_in_8bit directly when loading!

Architecture

The MoLA-LM architecture consists of:

Base Model: Qwen/Qwen3-4B-Thinking-2507
Router Network: Frozen encoder as Sentence transformer + decoder as MLP for adapter selection
LoRA Adapters: 9 task-specific fine-tuned adapters
Dynamic Switching: Automatic adapter application based on input

Paper coming soon™

Downloads last month: 596

Safetensors

Model size

4B params

Tensor type

F16

F32