Instructions to use CubicLabs/AXL-Micro-8M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CubicLabs/AXL-Micro-8M with Transformers:

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

pipe = pipeline("text-generation", model="CubicLabs/AXL-Micro-8M")

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("CubicLabs/AXL-Micro-8M", dtype="auto")

llama-cpp-python

How to use CubicLabs/AXL-Micro-8M with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="CubicLabs/AXL-Micro-8M",
	filename="axl-micro-llama-f16.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use CubicLabs/AXL-Micro-8M with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf CubicLabs/AXL-Micro-8M:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf CubicLabs/AXL-Micro-8M:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf CubicLabs/AXL-Micro-8M:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf CubicLabs/AXL-Micro-8M:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf CubicLabs/AXL-Micro-8M:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf CubicLabs/AXL-Micro-8M:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf CubicLabs/AXL-Micro-8M:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf CubicLabs/AXL-Micro-8M:Q4_K_M

Use Docker

docker model run hf.co/CubicLabs/AXL-Micro-8M:Q4_K_M

LM Studio
Jan

vLLM

How to use CubicLabs/AXL-Micro-8M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CubicLabs/AXL-Micro-8M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CubicLabs/AXL-Micro-8M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/CubicLabs/AXL-Micro-8M:Q4_K_M

SGLang

How to use CubicLabs/AXL-Micro-8M 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 "CubicLabs/AXL-Micro-8M" \
    --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": "CubicLabs/AXL-Micro-8M",
		"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 "CubicLabs/AXL-Micro-8M" \
        --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": "CubicLabs/AXL-Micro-8M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use CubicLabs/AXL-Micro-8M with Ollama:
```
ollama run hf.co/CubicLabs/AXL-Micro-8M:Q4_K_M
```

Unsloth Studio

How to use CubicLabs/AXL-Micro-8M 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 CubicLabs/AXL-Micro-8M 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 CubicLabs/AXL-Micro-8M to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for CubicLabs/AXL-Micro-8M to start chatting

Atomic Chat new
Docker Model Runner
How to use CubicLabs/AXL-Micro-8M with Docker Model Runner:
```
docker model run hf.co/CubicLabs/AXL-Micro-8M:Q4_K_M
```

Lemonade

How to use CubicLabs/AXL-Micro-8M with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull CubicLabs/AXL-Micro-8M:Q4_K_M

Run and chat with the model

lemonade run user.AXL-Micro-8M-Q4_K_M

List all available models

lemonade list

AXL-Micro-8M / config.json

KennedyOfficaly

Upload 12 files

19c6668 verified 3 months ago

Raw

History Blame Contribute Delete

772 Bytes

	{
	"model_type": "multiscale_transformer",
	"architectures": [
	"MultiScaleForCausalLM"
	],
	"vocab_size": 258,
	"d_model": 256,
	"n_heads": 4,
	"d_ff": 688,
	"n_layers_per_scale": 3,
	"n_cross_attn_layers": 1,
	"max_seq_len": 256,
	"dropout": 0.0,
	"bias": false,
	"rope_theta": 10000.0,
	"downsample_factors": [
	1,
	2,
	4
	],
	"num_parameters": 12003072,
	"training_results": {
	"model": "AXL-Micro-8M",
	"params": 12865792,
	"steps": 1723,
	"time": 600.0,
	"final_loss": 0.021,
	"perplexity": 3.13,
	"verified_perplexity": 3.13,
	"verified_date": "2026-03-28",
	"data": "synthetic Python code + Shakespeare",
	"optimizer": "AdamW",
	"device": "AMD Ryzen 5 5600G CPU"
	}
	}