Instructions to use LiquidAI/LFM2-24B-A2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use LiquidAI/LFM2-24B-A2B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="LiquidAI/LFM2-24B-A2B")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("LiquidAI/LFM2-24B-A2B", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use LiquidAI/LFM2-24B-A2B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "LiquidAI/LFM2-24B-A2B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "LiquidAI/LFM2-24B-A2B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/LiquidAI/LFM2-24B-A2B
- SGLang
How to use LiquidAI/LFM2-24B-A2B 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 "LiquidAI/LFM2-24B-A2B" \ --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": "LiquidAI/LFM2-24B-A2B", "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 "LiquidAI/LFM2-24B-A2B" \ --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": "LiquidAI/LFM2-24B-A2B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use LiquidAI/LFM2-24B-A2B with Docker Model Runner:
docker model run hf.co/LiquidAI/LFM2-24B-A2B
Actual use cases for this model
I'm interested to know: has anyone found real-world use-cases for this model?
I understand this is not a coding model but I still give models like that (very basic) coding tasks to ensure it can at least general internally consistent output, I took a simple task of converting 20 lines of pyspark to duckdb and gave it to both LFM2 and gpt-oss:20b. I gave both outputs to Grok to grade. LFM2 got 4.5/10 and gpt-oss got 8.5/10
I'm not impressed, I don't see any use-cases for this model given the ability of it's competition but maybe I'm being too narrow - has anyone found any good use cases for this model?
I am using it to assist in correcting scripting errors qwen3.5 made right now.
When people say 'coding model' i don't know what they mean anymore. What's a good coding chat partner isn't what's a good agent-ant.
The use case of this model is summarization, text analysis, research. It works pretty well. Is not created for coding, coding models are trained in massive code databases and focused in particular skills.
Closing this thread, no solid use-cases provided