Instructions to use FlameF0X/LFM2.5-1.2B-Distilled-Claude-4.6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FlameF0X/LFM2.5-1.2B-Distilled-Claude-4.6 with Transformers:

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

pipe = pipeline("text-generation", model="FlameF0X/LFM2.5-1.2B-Distilled-Claude-4.6")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FlameF0X/LFM2.5-1.2B-Distilled-Claude-4.6")
model = AutoModelForCausalLM.from_pretrained("FlameF0X/LFM2.5-1.2B-Distilled-Claude-4.6", 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 FlameF0X/LFM2.5-1.2B-Distilled-Claude-4.6 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FlameF0X/LFM2.5-1.2B-Distilled-Claude-4.6"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FlameF0X/LFM2.5-1.2B-Distilled-Claude-4.6",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FlameF0X/LFM2.5-1.2B-Distilled-Claude-4.6

SGLang

How to use FlameF0X/LFM2.5-1.2B-Distilled-Claude-4.6 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 "FlameF0X/LFM2.5-1.2B-Distilled-Claude-4.6" \
    --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": "FlameF0X/LFM2.5-1.2B-Distilled-Claude-4.6",
		"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 "FlameF0X/LFM2.5-1.2B-Distilled-Claude-4.6" \
        --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": "FlameF0X/LFM2.5-1.2B-Distilled-Claude-4.6",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use FlameF0X/LFM2.5-1.2B-Distilled-Claude-4.6 with Docker Model Runner:
```
docker model run hf.co/FlameF0X/LFM2.5-1.2B-Distilled-Claude-4.6
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model trained on Claude Sonnet 4.6 Adaptive Thinking (The claude.ai Claude, not the API Claude). The training data is PRIVATE.

LFM2.5-1.2B-Distilled-Claude-4.6 (Liquid Claude)

LFM2.5-1.2B-Distilled-Claude-4.6 (Liquid Claude) is a distillation of Claude into LFM2.5-1.2B-Thinking via LoRA.

Training data info:

THINK BLOCK PATTERNS
Agentic think blocks (Action/Observation): 8473
Pure reasoning think blocks: 3005

CONSECUTIVE USER MESSAGES
Total consecutive user-user pairs: 319

MESSAGE LENGTH STATS (chars)

:)	msgs	avg	max
System	2325	2168	2168
User	11919	332	39134
Assistant	11738	4386	264340

Assistant messages total: 11738
With agentic tool calls in think: 2151 (18.3%)

Total chars in dataset: 60,487,999
Approx tokens (~4 chars/token): 15,121,999

Conversations with <=2 messages (system+1): 121
Conversations with >5 think blocks in a single assistant msg: 319

Use model

from transformers import pipeline

pipe = pipeline("text-generation", model="FlameF0X/LFM2.5-1.2B-Distilled-Claude-4.6")
messages = [
    {"role": "system", "content": "You are a helpful assistant."}, # I RECOMMEND TO KEEP THIS FOR STABILITY! But you can change the system.
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

Sample chat:

(Ignore the fact that it took 1min to reason, i got a i3-6006u / 12GB as hardware and running the f16 quantization)

Benchmark

Model	Average	HellaSwag	MMLU	Piqa	Source
FlameF0X/LFM2.5-1.2B-Distilled-Claude-4.6	46.76	39.51	31.99	68.77	Intel/low bit open llm leaderboard
FlameF0X/LFM2.5-1.2B-Thinking-CodeX	45.25	39.70	26.56	69.48	As the one from above