Instructions to use sigargv/Laguna-M.1-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 sigargv/Laguna-M.1-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 sigargv/Laguna-M.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf sigargv/Laguna-M.1-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 sigargv/Laguna-M.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf sigargv/Laguna-M.1-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 sigargv/Laguna-M.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf sigargv/Laguna-M.1-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 sigargv/Laguna-M.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf sigargv/Laguna-M.1-GGUF:Q4_K_M

Use Docker

docker model run hf.co/sigargv/Laguna-M.1-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use sigargv/Laguna-M.1-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sigargv/Laguna-M.1-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": "sigargv/Laguna-M.1-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sigargv/Laguna-M.1-GGUF:Q4_K_M

Ollama
How to use sigargv/Laguna-M.1-GGUF with Ollama:
```
ollama run hf.co/sigargv/Laguna-M.1-GGUF:Q4_K_M
```

Unsloth Studio

How to use sigargv/Laguna-M.1-GGUF 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 sigargv/Laguna-M.1-GGUF 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 sigargv/Laguna-M.1-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for sigargv/Laguna-M.1-GGUF to start chatting

How to use sigargv/Laguna-M.1-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf sigargv/Laguna-M.1-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "sigargv/Laguna-M.1-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use sigargv/Laguna-M.1-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf sigargv/Laguna-M.1-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default sigargv/Laguna-M.1-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use sigargv/Laguna-M.1-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf sigargv/Laguna-M.1-GGUF:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "sigargv/Laguna-M.1-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use sigargv/Laguna-M.1-GGUF with Docker Model Runner:
```
docker model run hf.co/sigargv/Laguna-M.1-GGUF:Q4_K_M
```

Lemonade

How to use sigargv/Laguna-M.1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull sigargv/Laguna-M.1-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Laguna-M.1-GGUF-Q4_K_M

List all available models

lemonade list

sigargv commited on Jun 21

Commit

23fe633

verified ·

1 Parent(s): 2f5d866

Add Q8 BF16 and KL column to quant table

Browse files

Files changed (1) hide show

README.md +31 -24

README.md CHANGED Viewed

@@ -57,29 +57,34 @@ Poolside release.
 ## Quantization summary
-| Quant | Status | Size | PPL |
-| --- | ---: | ---: | ---: |
-| `IQ2_K_R4` | uploaded | 64.35 GiB | 2.6686 +/- 0.04561 |
-| `Q2_K` | uploaded | 77.67 GiB | pending |
-| `IQ2_M` | uploaded | 69.47 GiB | pending |
-| `IQ2_XS` | uploaded | 63.07 GiB | pending |
-| `IQ2_S` | uploaded | 63.08 GiB | pending |
-| `IQ3_K_R4` | uploaded | 91.81 GiB | 2.4770 +/- 0.04102 |
-| `IQ3_S` | uploaded | 91.81 GiB | 2.4683 +/- 0.04051 |
-| `IQ4_KS_R4` | uploaded | 113.20 GiB | 2.4140 +/- 0.03950 |
-| `IQ4_XS` | uploaded | 112.80 GiB | 2.4227 +/- 0.03976 |
-| `Q4_K_M` | uploaded | 127.33 GiB | 2.4084 +/- 0.03947 |
-| `Q5_K_M` | uploaded | 149.26 GiB | 2.4085 +/- 0.03954 |
-| `Q6_K` | evaluating | 172.82 GiB | pending |
-| `IQ1_S` | queued | pending | pending |
-| `IQ1_S_R4` | queued | pending | pending |
-| `IQ1_KT` | queued | pending | pending |
-| `IQ4_K_R4` | queued | pending | pending |
-| `IQ5_KS_R4` | queued | pending | pending |
-| `IQ5_K_R4` | queued | pending | pending |
-| `IQ5_KS` | queued | pending | pending |
-| `IQ5_K` | queued | pending | pending |
-| `IQ6_K` | queued | pending | pending |
 ## Imatrix and calibration corpus
@@ -153,7 +158,9 @@ the earlier ad hoc `laguna-m1-code-calib.txt` were deliberately excluded.
 ## Metrics
-The PPL numbers in the table are measured by `llama-perplexity` on a fixed slice of the public calibration corpus. They are intended as reproducibility and regression checks for these artifacts, not as a general benchmark of Laguna M.1.
 Validation tries full GPU offload first and falls back to lower `-ngl` values if
 the quant is too large for full offload on the validation machine. Each quant's

 ## Quantization summary
+| Quant | Status | Size | PPL | KL divergence |
+| --- | ---: | ---: | ---: | ---: |
+| `IQ1_S` | queued | pending | pending | pending |
+| `IQ1_S_R4` | queued | pending | pending | pending |
+| `IQ1_KT` | queued | pending | pending | pending |
+| `IQ2_XS` | uploaded | 63.07 GiB | pending | pending |
+| `IQ2_S` | uploaded | 63.08 GiB | pending | pending |
+| `IQ2_K_R4` | uploaded | 64.35 GiB | 2.6686 +/- 0.04561 | pending |
+| `IQ2_M` | uploaded | 69.47 GiB | pending | pending |
+| `Q2_K` | uploaded | 77.67 GiB | pending | pending |
+| `IQ3_S` | uploaded | 91.81 GiB | 2.4683 +/- 0.04051 | pending |
+| `IQ3_K_R4` | uploaded | 91.81 GiB | 2.4770 +/- 0.04102 | pending |
+| `IQ4_XS` | uploaded | 112.80 GiB | 2.4227 +/- 0.03976 | pending |
+| `IQ4_KS_R4` | uploaded | 113.20 GiB | 2.4140 +/- 0.03950 | pending |
+| `IQ4_K_R4` | queued | pending | pending | pending |
+| `Q4_K_M` | uploaded | 127.33 GiB | 2.4084 +/- 0.03947 | pending |
+| `IQ5_KS` | queued | pending | pending | pending |
+| `IQ5_KS_R4` | queued | pending | pending | pending |
+| `IQ5_K` | queued | pending | pending | pending |
+| `IQ5_K_R4` | queued | pending | pending | pending |
+| `Q5_K_M` | uploaded | 149.26 GiB | 2.4085 +/- 0.03954 | pending |
+| `IQ6_K` | queued | pending | pending | pending |
+| `Q6_K` | finished | 172.82 GiB | 2.4368 +/- 0.04032 | pending |
+| `Q8_0` | uploading | 223.63 GiB | pending | pending |
+| `BF16` | local source | 420.71 GiB | pending | pending |
+Rows are ordered by effective bit-width. Queued rows with pending sizes are
+placed by quant family and expected BPW.
 ## Imatrix and calibration corpus
 ## Metrics
+The PPL and KL divergence numbers in the table are measured on a fixed slice of
+the public calibration corpus. They are intended as reproducibility and
+regression checks for these artifacts, not as a general benchmark of Laguna M.1.
 Validation tries full GPU offload first and falls back to lower `-ngl` values if
 the quant is too large for full offload on the validation machine. Each quant's