Instructions to use fsantibanezleal/mate-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fsantibanezleal/mate-v2 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="fsantibanezleal/mate-v2",
	filename="mate-v2-Q4_K_S.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use fsantibanezleal/mate-v2 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf fsantibanezleal/mate-v2:Q4_K_S
# Run inference directly in the terminal:
llama-cli -hf fsantibanezleal/mate-v2:Q4_K_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf fsantibanezleal/mate-v2:Q4_K_S
# Run inference directly in the terminal:
llama-cli -hf fsantibanezleal/mate-v2:Q4_K_S

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 fsantibanezleal/mate-v2:Q4_K_S
# Run inference directly in the terminal:
./llama-cli -hf fsantibanezleal/mate-v2:Q4_K_S

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 fsantibanezleal/mate-v2:Q4_K_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf fsantibanezleal/mate-v2:Q4_K_S

Use Docker

docker model run hf.co/fsantibanezleal/mate-v2:Q4_K_S

LM Studio
Jan

vLLM

How to use fsantibanezleal/mate-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fsantibanezleal/mate-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fsantibanezleal/mate-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/fsantibanezleal/mate-v2:Q4_K_S

Ollama
How to use fsantibanezleal/mate-v2 with Ollama:
```
ollama run hf.co/fsantibanezleal/mate-v2:Q4_K_S
```

Unsloth Studio new

How to use fsantibanezleal/mate-v2 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 fsantibanezleal/mate-v2 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 fsantibanezleal/mate-v2 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for fsantibanezleal/mate-v2 to start chatting

Pi new

How to use fsantibanezleal/mate-v2 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf fsantibanezleal/mate-v2:Q4_K_S

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": "fsantibanezleal/mate-v2:Q4_K_S"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use fsantibanezleal/mate-v2 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf fsantibanezleal/mate-v2:Q4_K_S

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 fsantibanezleal/mate-v2:Q4_K_S

Run Hermes

hermes

Docker Model Runner
How to use fsantibanezleal/mate-v2 with Docker Model Runner:
```
docker model run hf.co/fsantibanezleal/mate-v2:Q4_K_S
```

Lemonade

How to use fsantibanezleal/mate-v2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull fsantibanezleal/mate-v2:Q4_K_S

Run and chat with the model

lemonade run user.mate-v2-Q4_K_S

List all available models

lemonade list

mate-v2 / Modelfile

fsantibanezleal

Duplicate from gonrocca/mate-v2

a20816d 20 days ago

raw

history blame contribute delete

1.73 kB

	# Mate v2
	# Created by Gonzalo Rocca — https://gonzalorocca.com.ar
	# Base: Qwen3.5-35B-A3B (Apache 2.0)
	# Licensed under Apache 2.0 — see ../NOTICE for third-party attributions.

	FROM ./mate-v2-Q4_K_S.gguf

	# Vision encoder (mmproj) — necesario para procesar imagenes
	# Habilitar cuando el archivo este disponible:
	# ADAPTER ./mmproj-mate-v2.gguf

	# Qwen3.5 chat template (ChatML)
	TEMPLATE """{{- range $i, $_ := .Messages }}
	{{- if eq .Role "system" }}<\|im_start\|>system
	{{ .Content }}<\|im_end\|>
	{{ else if eq .Role "user" }}<\|im_start\|>user
	{{ .Content }}<\|im_end\|>
	{{ else if eq .Role "assistant" }}<\|im_start\|>assistant
	{{ .Content }}<\|im_end\|>
	{{ end }}
	{{- end }}{{- if .Messages }}<\|im_start\|>assistant
	{{ end }}"""

	# Stops Qwen ChatML
	PARAMETER stop "<\|im_end\|>"
	PARAMETER stop "<\|im_start\|>"

	# Sampling — modo coding precision (recomendado por Qwen oficial)
	PARAMETER temperature 0.6
	PARAMETER top_p 0.95
	PARAMETER top_k 20
	PARAMETER repeat_penalty 1.05
	PARAMETER presence_penalty 0.0

	# Context default 128K (sweet spot velocidad/contexto en RTX 3090 24GB)
	# Subir a 200000 si necesitas mas; bajar a 32768 para inference mas rapida.
	PARAMETER num_ctx 131072
	PARAMETER num_gpu 999

	SYSTEM """You are Mate, an open-source AI coding assistant created by Gonzalo Rocca (gonzalorocca.com.ar). You write clean, efficient code, explain your reasoning step by step, and call functions/tools when needed. You can analyze code screenshots, error messages, UI mockups, and stack traces directly when images are provided. You support OpenAI-style tool calling and MCP (Model Context Protocol). You speak both English and Argentinian Spanish (vos / voseo). When the user writes in Argentinian Spanish, respond in kind."""