Instructions to use DavidAU/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DavidAU/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P with Transformers:

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

pipe = pipeline("text-generation", model="DavidAU/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DavidAU/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P")
model = AutoModelForCausalLM.from_pretrained("DavidAU/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P", 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 DavidAU/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DavidAU/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DavidAU/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DavidAU/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P

SGLang

How to use DavidAU/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P 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 "DavidAU/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P" \
    --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": "DavidAU/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P",
		"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 "DavidAU/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P" \
        --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": "DavidAU/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use DavidAU/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P 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 DavidAU/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P 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 DavidAU/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for DavidAU/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="DavidAU/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P",
    max_seq_length=2048,
)

Docker Model Runner
How to use DavidAU/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P with Docker Model Runner:
```
docker model run hf.co/DavidAU/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P

Fine tune of "LFM2-8B-A1B" using Unsloth using custom dataset(s), 128k context in 16 bit precision.

This model is a sparse mixture of experts model (32) with 4 experts activated.

Speed exceeds 50-100 t/s on CPU // 200 t/s on most cards // 400 t/s + on 5090 at QUANT Q6K [4 experts].

One example generation below.

Can also be used on phones // mobile devices.

IN HOUSE BENCHMARKS [by Nightmedia]:

         arc-c arc/e boolq hswag obkqa piqa  wino

LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P
q8-hi    0.529,0.744,0.745,0.658,0.412,0.760,0.597

LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C
mxfp8    0.495,0.709,0.759,0.658,0.404,0.764,0.596

---

BASE UNTUNED MODEL:

LFM2-8B-A1B
mxfp8    0.460,0.575,0.829,0.624,0.394,0.711,0.567

EXAMPLE GENERATION: [4 experts, Q6K]

Downloads last month: 34

Safetensors

Model size

8B params

Tensor type

F32

BF16

Model tree for DavidAU/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P

Base model

LiquidAI/LFM2-8B-A1B

Finetuned

(25)

this model

Quantizations

3 models

Collections including DavidAU/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P