Instructions to use specklabs/Speck1.5-140M-Instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use specklabs/Speck1.5-140M-Instruct-GGUF 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 specklabs/Speck1.5-140M-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf specklabs/Speck1.5-140M-Instruct-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf specklabs/Speck1.5-140M-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf specklabs/Speck1.5-140M-Instruct-GGUF: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 specklabs/Speck1.5-140M-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf specklabs/Speck1.5-140M-Instruct-GGUF: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 specklabs/Speck1.5-140M-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf specklabs/Speck1.5-140M-Instruct-GGUF:Q4_K_M

Use Docker

docker model run hf.co/specklabs/Speck1.5-140M-Instruct-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use specklabs/Speck1.5-140M-Instruct-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "specklabs/Speck1.5-140M-Instruct-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "specklabs/Speck1.5-140M-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/specklabs/Speck1.5-140M-Instruct-GGUF:Q4_K_M

Ollama
How to use specklabs/Speck1.5-140M-Instruct-GGUF with Ollama:
```
ollama run hf.co/specklabs/Speck1.5-140M-Instruct-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use specklabs/Speck1.5-140M-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/specklabs/Speck1.5-140M-Instruct-GGUF:Q4_K_M
```

Lemonade

How to use specklabs/Speck1.5-140M-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull specklabs/Speck1.5-140M-Instruct-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Speck1.5-140M-Instruct-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

Speck1.5-140M-Instruct GGUF

llama.cpp-compatible GGUF builds of specklabs/Speck1.5-140M-Instruct, pinned to source revision 2b341f20dd6c8bed9955c9a11be18b302c5110ad.

File	Quantization	Size
Speck1.5-140M-Instruct-BF16.gguf	BF16	361.2 MB
Speck1.5-140M-Instruct-Q4_K_M.gguf	Q4_K_M	112.9 MB
Speck1.5-140M-Instruct-Q5_K_M.gguf	Q5_K_M	130.3 MB
Speck1.5-140M-Instruct-Q8_0.gguf	Q8_0	192.4 MB

Usage

llama-cli -hf specklabs/Speck1.5-140M-Instruct-GGUF:Q4_K_M -cnv

The source Speck architecture and llama.cpp's LFM2 runtime implement the same alternating attention/short-convolution operators. Conversion folds the 640-to-768 input and 768-to-640 output adapters into the embeddings, zero-pads the 384-wide convolution channels to 768, and left-pads 3-tap causal kernels to 5 taps. These transformations preserve the model function apart from normal floating-point and quantization rounding.

The GGUF graph stores 180,165,376 parameters because the source's tied 640-wide embedding and two adapters become separate 768-wide input and output matrices. This compatibility transform does not add layers or model capacity.

The conversion was built with llama.cpp revision 2e88c49c90f0add8796f633fea8c3d65b975f295. Exact checksums and conversion provenance are in conversion.json.