Instructions to use MainStack/marvy-1-14B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MainStack/marvy-1-14B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="MainStack/marvy-1-14B-GGUF",
	filename="marvy-14B-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use MainStack/marvy-1-14B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf MainStack/marvy-1-14B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf MainStack/marvy-1-14B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf MainStack/marvy-1-14B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf MainStack/marvy-1-14B-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 MainStack/marvy-1-14B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf MainStack/marvy-1-14B-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 MainStack/marvy-1-14B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf MainStack/marvy-1-14B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/MainStack/marvy-1-14B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use MainStack/marvy-1-14B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MainStack/marvy-1-14B-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": "MainStack/marvy-1-14B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MainStack/marvy-1-14B-GGUF:Q4_K_M

Ollama
How to use MainStack/marvy-1-14B-GGUF with Ollama:
```
ollama run hf.co/MainStack/marvy-1-14B-GGUF:Q4_K_M
```

Unsloth Studio

How to use MainStack/marvy-1-14B-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 MainStack/marvy-1-14B-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 MainStack/marvy-1-14B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for MainStack/marvy-1-14B-GGUF to start chatting

How to use MainStack/marvy-1-14B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf MainStack/marvy-1-14B-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": "MainStack/marvy-1-14B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use MainStack/marvy-1-14B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf MainStack/marvy-1-14B-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 MainStack/marvy-1-14B-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use MainStack/marvy-1-14B-GGUF with Docker Model Runner:
```
docker model run hf.co/MainStack/marvy-1-14B-GGUF:Q4_K_M
```

Lemonade

How to use MainStack/marvy-1-14B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull MainStack/marvy-1-14B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.marvy-1-14B-GGUF-Q4_K_M

List all available models

lemonade list

tgetsov commited on 6 days ago

Commit

81b1a6d

verified ·

1 Parent(s): f5a43f2

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +11 -11

README.md CHANGED Viewed

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: MainStack/marvy-14B
 base_model_relation: quantized
 pipeline_tag: text-generation
 language:
@@ -17,11 +17,11 @@ tags:
   - qwen2.5
 ---
-# marvy-14B-GGUF
-**GGUF quants of marvy-14B, the first open LLM for the full ServiceNow delivery lifecycle. Run it locally and privately on Apple Silicon, LM Studio, or Ollama.**
-GGUF quantizations of [`MainStack/marvy-14B`](https://huggingface.co/MainStack/marvy-14B)
 for use with [llama.cpp](https://github.com/ggerganov/llama.cpp),
 [Ollama](https://ollama.com), [LM Studio](https://lmstudio.ai), and compatible runtimes.
@@ -31,30 +31,30 @@ for use with [llama.cpp](https://github.com/ggerganov/llama.cpp),
 | File | Quant | Size (approx) | Use when |
 |---|---|---|---|
-| `marvy-14B-Q4_K_M.gguf` | Q4_K_M | ~9 GB | Default — best size/quality balance, laptops |
-| `marvy-14B-Q8_0.gguf`   | Q8_0   | ~16 GB | Highest fidelity, near-FP16 quality |
 ## Quick start
 ### Ollama
 ```bash
-ollama run hf.co/MainStack/marvy-14B-GGUF:Q4_K_M
 ```
 ### llama.cpp
 ```bash
-./llama-cli -hf MainStack/marvy-14B-GGUF:Q4_K_M \
   -p "Write a ServiceNow user story with acceptance criteria for P1 SLA escalation." \
   --temp 0.4
 ```
 ### LM Studio
-1. In the model browser, search `MainStack/marvy-14B-GGUF` and download a quant
    (`Q4_K_M` recommended), **or** drop the `.gguf` into
-   `~/.lmstudio/models/MainStack/marvy-14B-GGUF/`.
 2. Load it, set the system prompt below, temperature ~0.4.
 3. To use from code/OpenCode, start the local server:
    ```bash
@@ -82,7 +82,7 @@ professional English.
 ## Provenance & limitations
-See the [merged model card](https://huggingface.co/MainStack/marvy-14B) for the
 full training data, anonymization methodology, evaluation (test ppl 13.107 on a
 project-disjoint split), and limitations. Quantization adds the usual minor
 quality reduction versus the FP16 model.

 ---
 license: apache-2.0
+base_model: MainStack/marvy-1-14B
 base_model_relation: quantized
 pipeline_tag: text-generation
 language:
   - qwen2.5
 ---
+# marvy-1-14B-GGUF
+**GGUF quants of marvy-1-14B, the first open LLM for the full ServiceNow delivery lifecycle. Run it locally and privately on Apple Silicon, LM Studio, or Ollama.**
+GGUF quantizations of [`MainStack/marvy-1-14B`](https://huggingface.co/MainStack/marvy-1-14B)
 for use with [llama.cpp](https://github.com/ggerganov/llama.cpp),
 [Ollama](https://ollama.com), [LM Studio](https://lmstudio.ai), and compatible runtimes.
 | File | Quant | Size (approx) | Use when |
 |---|---|---|---|
+| `marvy-1-14B-Q4_K_M.gguf` | Q4_K_M | ~9 GB | Default — best size/quality balance, laptops |
+| `marvy-1-14B-Q8_0.gguf`   | Q8_0   | ~16 GB | Highest fidelity, near-FP16 quality |
 ## Quick start
 ### Ollama
 ```bash
+ollama run hf.co/MainStack/marvy-1-14B-GGUF:Q4_K_M
 ```
 ### llama.cpp
 ```bash
+./llama-cli -hf MainStack/marvy-1-14B-GGUF:Q4_K_M \
   -p "Write a ServiceNow user story with acceptance criteria for P1 SLA escalation." \
   --temp 0.4
 ```
 ### LM Studio
+1. In the model browser, search `MainStack/marvy-1-14B-GGUF` and download a quant
    (`Q4_K_M` recommended), **or** drop the `.gguf` into
+   `~/.lmstudio/models/MainStack/marvy-1-14B-GGUF/`.
 2. Load it, set the system prompt below, temperature ~0.4.
 3. To use from code/OpenCode, start the local server:
    ```bash
 ## Provenance & limitations
+See the [merged model card](https://huggingface.co/MainStack/marvy-1-14B) for the
 full training data, anonymization methodology, evaluation (test ppl 13.107 on a
 project-disjoint split), and limitations. Quantization adds the usual minor
 quality reduction versus the FP16 model.