Instructions to use Nichonauta/LFM2.5-1.2B-Thinking-ToMoE-INT8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Nichonauta/LFM2.5-1.2B-Thinking-ToMoE-INT8 with Transformers:

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

pipe = pipeline("text-generation", model="Nichonauta/LFM2.5-1.2B-Thinking-ToMoE-INT8", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Nichonauta/LFM2.5-1.2B-Thinking-ToMoE-INT8", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Nichonauta/LFM2.5-1.2B-Thinking-ToMoE-INT8", trust_remote_code=True, 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 Nichonauta/LFM2.5-1.2B-Thinking-ToMoE-INT8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Nichonauta/LFM2.5-1.2B-Thinking-ToMoE-INT8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Nichonauta/LFM2.5-1.2B-Thinking-ToMoE-INT8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Nichonauta/LFM2.5-1.2B-Thinking-ToMoE-INT8

SGLang

How to use Nichonauta/LFM2.5-1.2B-Thinking-ToMoE-INT8 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 "Nichonauta/LFM2.5-1.2B-Thinking-ToMoE-INT8" \
    --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": "Nichonauta/LFM2.5-1.2B-Thinking-ToMoE-INT8",
		"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 "Nichonauta/LFM2.5-1.2B-Thinking-ToMoE-INT8" \
        --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": "Nichonauta/LFM2.5-1.2B-Thinking-ToMoE-INT8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Nichonauta/LFM2.5-1.2B-Thinking-ToMoE-INT8 with Docker Model Runner:
```
docker model run hf.co/Nichonauta/LFM2.5-1.2B-Thinking-ToMoE-INT8
```

LFM2.5-1.2B-Thinking-ToMoE-INT8

Weight-only INT8 quantization of the real ToMoE MoE — Nichonauta/LFM2.5-1.2B-Thinking-ToMoE (derived from LiquidAI/LFM2.5-1.2B-Thinking).

Unlike the GGUF companions (which are dense-equivalents because llama.cpp cannot represent the channel-MoE), this repository stores the actual pruned MoE weights quantized in safetensors format:

LinearINT8 replaces the MLP/attention/conv Linear layers (per-channel symmetric for INT8; per-group of 64 with zero-point for INT4), packed 2-nibbles-per-byte for INT4.
The routers, embeddings and norms stay fp32 (tiny and sensitive); weights dequantize lazily in the forward pass.
Same custom model definition (modeling_lfm2_moe_final.py, trust_remote_code), plus the quantization flag in config.json.

Metrics vs the fp32 MoE

Metric	fp32 MoE	INT8	INT4
PPL wikitext-2 (raw, 1810 tok)	504	504	504
PPL chat-formatted (prompt+answer)	712	709	723
`model.safetensors` size	4230 MB	1376 MB	—

The 1.2B MoE is robust to weight-only quantization: INT8 and INT4 are within measurement noise of the fp32 MoE (raw PPL identical, chat within ~1.5%).

Usage (transformers, trust_remote_code)

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "Nichonauta/LFM2.5-1.2B-Thinking-ToMoE-INT8",
    trust_remote_code=True,
    torch_dtype=torch.bfloat16,
    device_map="cuda:0",
    attn_implementation="eager",
)
tokenizer = AutoTokenizer.from_pretrained("Nichonauta/LFM2.5-1.2B-Thinking-ToMoE-INT8")

The quantization field in config.json makes the custom modeling file build the quantized Linear layers automatically.

Files

model.safetensors — INT8 weights + fp32 scales/zero-points + fp32 routers/embeddings/buffers
modeling_lfm2_moe_final.py — custom model definition with LinearINT8 support (trust_remote_code)
config.json — model configuration (quantization: "int8", auto_map)
tokenizer.json, tokenizer_config.json, chat_template.jinja, generation_config.json, LICENSE

License

Derivative of LiquidAI/LFM2.5-1.2B-Thinking — released under the LFM Open License v1.0 (see LICENSE).

Downloads last month: 32

Safetensors

Model size

1B params

Tensor type

I64

F32

Model tree for Nichonauta/LFM2.5-1.2B-Thinking-ToMoE-INT8

Base model

LiquidAI/LFM2.5-1.2B-Base

Finetuned

LiquidAI/LFM2.5-1.2B-Thinking

Finetuned

Nichonauta/LFM2.5-1.2B-Thinking-ToMoE

Finetuned

(2)

this model