Instructions to use CubicLabs/AXL-Coder-15M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CubicLabs/AXL-Coder-15M with Transformers:

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

pipe = pipeline("text-generation", model="CubicLabs/AXL-Coder-15M")

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("CubicLabs/AXL-Coder-15M", dtype="auto")

llama-cpp-python

How to use CubicLabs/AXL-Coder-15M with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="CubicLabs/AXL-Coder-15M",
	filename="axl-coder-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-Coder-15M 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-Coder-15M:F16
# Run inference directly in the terminal:
llama cli -hf CubicLabs/AXL-Coder-15M:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf CubicLabs/AXL-Coder-15M:F16
# Run inference directly in the terminal:
llama cli -hf CubicLabs/AXL-Coder-15M:F16

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-Coder-15M:F16
# Run inference directly in the terminal:
./llama-cli -hf CubicLabs/AXL-Coder-15M:F16

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-Coder-15M:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf CubicLabs/AXL-Coder-15M:F16

Use Docker

docker model run hf.co/CubicLabs/AXL-Coder-15M:F16

LM Studio
Jan

vLLM

How to use CubicLabs/AXL-Coder-15M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CubicLabs/AXL-Coder-15M"
# 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-Coder-15M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/CubicLabs/AXL-Coder-15M:F16

SGLang

How to use CubicLabs/AXL-Coder-15M 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-Coder-15M" \
    --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-Coder-15M",
		"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-Coder-15M" \
        --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-Coder-15M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use CubicLabs/AXL-Coder-15M with Ollama:
```
ollama run hf.co/CubicLabs/AXL-Coder-15M:F16
```

Unsloth Studio

How to use CubicLabs/AXL-Coder-15M 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-Coder-15M 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-Coder-15M 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-Coder-15M to start chatting

Atomic Chat new
Docker Model Runner
How to use CubicLabs/AXL-Coder-15M with Docker Model Runner:
```
docker model run hf.co/CubicLabs/AXL-Coder-15M:F16
```

Lemonade

How to use CubicLabs/AXL-Coder-15M with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull CubicLabs/AXL-Coder-15M:F16

Run and chat with the model

lemonade run user.AXL-Coder-15M-F16

List all available models

lemonade list

Restrictated commited on about 14 hours ago

Commit

4e16560

verified ·

1 Parent(s): 2e6a6e2

Update README.md

Browse files

Files changed (1) hide show

README.md +8 -8

README.md CHANGED Viewed

@@ -6,7 +6,7 @@ tags:
   - code-generation
   - multi-scale-transformer
   - cpu-optimized
-  - koinic
   - pytorch
   - llama
   - gguf
@@ -32,13 +32,13 @@ model-index:
 # AXL-Coder-15M
-Agentic coding. 26M params. PPL 1.54. 8-action tool router. Part of the AXL model family by [KoinicLabs](https://huggingface.co/KoinicLabs).
 ## Model Details
 | Property | Value |
 |----------|-------|
-| Developed by | [KoinicLabs](https://huggingface.co/KoinicLabs) |
 | Architecture | Multi-Scale Transformer |
 | Parameters | 26M |
 | Optimizer | SGD |
@@ -53,8 +53,8 @@ Agentic coding. 26M params. PPL 1.54. 8-action tool router. Part of the AXL mode
 ### Sources
-- **Repository:** [GitHub](https://github.com/Koinic/AXL)
-- **Organization:** [KoinicLabs](https://huggingface.co/KoinicLabs)
 ## Uses
@@ -154,9 +154,9 @@ Multi-Scale Transformer with three parallel encoder stacks at resolution scales
 ```bibtex
 @misc{axl_2026,
   title={AXL: AXL-Coder-15M - Multi-Scale Transformer for CPU Code Generation},
-  author={Koinic},
   year={2026},
-  url={https://huggingface.co/KoinicLabs}
 }
 ```
@@ -187,4 +187,4 @@ ids = torch.tensor([tokenizer.encode(prompt)], dtype=torch.long)
 with torch.no_grad():
     out = model.generate(ids, max_new_tokens=100, temperature=0.8, top_k=40)
 print(tokenizer.decode(out[0].tolist()))
-```

   - code-generation
   - multi-scale-transformer
   - cpu-optimized
+  - cubic
   - pytorch
   - llama
   - gguf
 # AXL-Coder-15M
+Agentic coding. 26M params. PPL 1.54. 8-action tool router. Part of the AXL model family by [CubicLabs](https://huggingface.co/CubicLabs).
 ## Model Details
 | Property | Value |
 |----------|-------|
+| Developed by | [CubicLabs](https://huggingface.co/CubicLabs) |
 | Architecture | Multi-Scale Transformer |
 | Parameters | 26M |
 | Optimizer | SGD |
 ### Sources
+- **Repository:** [GitHub](https://github.com/Cubic/AXL)
+- **Organization:** [CubicLabs](https://huggingface.co/CubicLabs)
 ## Uses
 ```bibtex
 @misc{axl_2026,
   title={AXL: AXL-Coder-15M - Multi-Scale Transformer for CPU Code Generation},
+  author={Cubic},
   year={2026},
+  url={[https://huggingface.co/CubicLabs](https://huggingface.co/CubicLabs)}
 }
 ```
 with torch.no_grad():
     out = model.generate(ids, max_new_tokens=100, temperature=0.8, top_k=40)
 print(tokenizer.decode(out[0].tolist()))
+```