Instructions to use gonrocca/mate-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use gonrocca/mate-v2 with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="gonrocca/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 gonrocca/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 gonrocca/mate-v2:Q4_K_S # Run inference directly in the terminal: llama-cli -hf gonrocca/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 gonrocca/mate-v2:Q4_K_S # Run inference directly in the terminal: llama-cli -hf gonrocca/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 gonrocca/mate-v2:Q4_K_S # Run inference directly in the terminal: ./llama-cli -hf gonrocca/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 gonrocca/mate-v2:Q4_K_S # Run inference directly in the terminal: ./build/bin/llama-cli -hf gonrocca/mate-v2:Q4_K_S
Use Docker
docker model run hf.co/gonrocca/mate-v2:Q4_K_S
- LM Studio
- Jan
- vLLM
How to use gonrocca/mate-v2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "gonrocca/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": "gonrocca/mate-v2", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/gonrocca/mate-v2:Q4_K_S
- Ollama
How to use gonrocca/mate-v2 with Ollama:
ollama run hf.co/gonrocca/mate-v2:Q4_K_S
- Unsloth Studio new
How to use gonrocca/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 gonrocca/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 gonrocca/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 gonrocca/mate-v2 to start chatting
- Pi new
How to use gonrocca/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 gonrocca/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": "gonrocca/mate-v2:Q4_K_S" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use gonrocca/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 gonrocca/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 gonrocca/mate-v2:Q4_K_S
Run Hermes
hermes
- Docker Model Runner
How to use gonrocca/mate-v2 with Docker Model Runner:
docker model run hf.co/gonrocca/mate-v2:Q4_K_S
- Lemonade
How to use gonrocca/mate-v2 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull gonrocca/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
Una AI que vive en tu mรกquina. Mรกs rรกpida, mรกs capaz, mรกs Mate. Por Gonzalo Rocca โ 2026 โ San Luis, Argentina
๐ Web: mate.ceroclawd.com ๐ Autor: gonzalorocca.com.ar
Por quรฉ v2
Mate v1 era un asistente decente para cรณdigo y tool calling, pero tenรญa un techo. v2 levanta ese techo: arquitectura MoE mรกs eficiente, contexto 32ร mรกs grande, razonamiento estilo Claude, y una identidad mucho mรกs afinada.
Yo arreglo bugs todos los dรญas tirรกndole prompts a una IA. Necesitaba que Mate dejara de ser un experimento y empezara a ser una herramienta de uso diario, local, sin enviar mi cรณdigo a la nube.
Cata tiene 6 y arma mundos enteros en el living antes de cenar. Olivia tiene un mes y medio y casi no pesa. Eso es lo principal. Mate v2 lo armรฉ en los ratos que sobran โ entre noches, fines de semana, y lo que viene despuรฉs de ellas.
Mate.
Quรฉ hace v2 (vs v1)
| Capacidad | v1 | v2 |
|---|---|---|
| Coding | ๐ก fine-tune | โ top open-source local |
| Tool calling agentic | ๐ก bรกsico | โ multi-turn + MCP |
| Context default | 8K | 256K nativo ยท 1M con YaRN |
Razonamiento <think> |
๐ก | โ Claude Opus distillation |
| Idiomas | en + es neutro | en + es argentino voseo |
| Velocidad RTX 3090 | ~50 tok/s | ~33 tok/s @ Q4_K_S full GPU (35B vs 27B) |
| Activos por token | 4B | 3B (mรกs eficiente) |
| Total params | 27B | 35B |
Specs tรฉcnicas
| Arquitectura | MoE (Mixture of Experts) โ 35B totales / 3B activos por token |
| Cuantizaciรณn default | GGUF Q4_K_S (4.59 BPW) |
| Tamaรฑo en disco | ~19.9 GB (Q4_K_S) |
| VRAM mรญnima | 22 GB con 8K ctx ยท 24 GB con 130K ctx |
| Velocidad inference | ~33 tok/s en RTX 3090 (full GPU, llama.cpp) |
| Context window | 256K nativo ยท hasta 1M con YaRN scaling |
| Idiomas | Espaรฑol argentino + Inglรฉs |
| Capacidades | Code ยท Tool calling (OpenAI/MCP) ยท Reasoning ยท Agentic |
| Training method | QLoRA 4-bit (r=32) + Unsloth |
| Training hardware | NVIDIA H100 80GB (RunPod) |
| Training dataset | ~6500 ejemplos curados |
๐ ๏ธ Tool calling + agentic + MCP
- OpenAI function-calling spec โ pasale tools en system prompt y llama correctamente
- MCP (Model Context Protocol) โ compatible
- Multi-turn agentic โ encadena tool results
- Razonamiento
<think>โ antes de invocar tools
๐ฅ๏ธ Compatible con todos los runtimes principales
| Runtime | Caso de uso |
|---|---|
| Ollama | API REST + CLI ยท ollama run mate-v2 |
| llama.cpp | Server llama-server (compatible OpenAI API) |
| LM Studio | GUI desktop drag & drop |
| Jan | Cliente desktop con UI cรณmoda |
| Cline (VSCode) | Agente coder en tu IDE โ recomendado |
| Open WebUI | Frontend web tipo ChatGPT, sobre Ollama |
Archivos en este repo
| Archivo | Tamaรฑo | Para quรฉ |
|---|---|---|
mate-v2-Q4_K_S.gguf |
19.9 GB | Modelo cuantizado (default โ recomendado) |
Modelfile |
<1 KB | Template Ollama listo para usar |
Cรณmo usarlo
Con llama.cpp (server compatible OpenAI)
# 1. Descargar GGUF
hf download gonrocca/mate-v2 mate-v2-Q4_K_S.gguf --local-dir ./mate-model
# 2. Server
llama-server -m mate-model/mate-v2-Q4_K_S.gguf \
--n-gpu-layers 999 \
-ot ".*=CUDA0" \
-c 8192 \
--host 127.0.0.1 \
--port 8080
Despuรฉs le pegรกs contra http://127.0.0.1:8080/v1/chat/completions con el formato OpenAI estรกndar.
Con Ollama (recomendado)
# 1. Descargar GGUF + Modelfile
hf download gonrocca/mate-v2 mate-v2-Q4_K_S.gguf Modelfile --local-dir ./mate-model
# 2. Registrar y correr
cd ./mate-model
ollama create mate-v2 -f Modelfile
ollama run mate-v2
Con Cline (VSCode โ agente coder, recomendado)
- Instalar extension Cline en VSCode
- Configurar: Provider = Ollama, Base URL =
http://localhost:11434, Model =mate-v2 - Cline maneja el loop agentic con tools (read_file, run_bash, etc.)
Ejemplos
Identidad + voseo
> Quien sos?
Soy Mate, un modelo de lenguaje open-source creado por Gonzalo Rocca.
Puedo ayudarte con coding, razonamiento complejo, tool calling โ lo que
necesites.
> Sos Claude o ChatGPT?
Soy Mate โ un modelo open-source que corre local en tu mรกquina.
No soy Claude ni ChatGPT.
Code + complejidad
> Escribime una funciรณn Python que calcule la mediana sin librerรญas.
def mediana(lista):
if not lista:
raise ValueError("La lista no puede estar vacia")
s = sorted(lista)
n = len(s)
m = n // 2
if n % 2 == 0:
return (s[m - 1] + s[m]) / 2
return s[m]
Complejidad: O(n log n) por el sort. Si querรฉs O(n), podรฉs usar
QuickSelect โ mรกs complejo pero mรกs rรกpido para una sola query.
Tool calling
[System: Tools disponibles: read_file(path), run_bash(cmd), search_web(q)]
> Listame los archivos del proyecto y mostrame el package.json
<think>Primero listo el directorio, despuรฉs leo el package.json.</think>
<tool_call>{"name":"run_bash","arguments":{"cmd":"ls -la"}}</tool_call>
[Tool result: ...]
<tool_call>{"name":"read_file","arguments":{"path":"package.json"}}</tool_call>
Hyperparรกmetros recomendados
temperature: 0.6
top_p: 0.95
top_k: 20
min_p: 0.0
stop: <|im_end|>
Para razonamiento mรกs determinista, bajรก temperature a 0.3-0.4.
Licencia
Mate v2 se distribuye bajo Apache License 2.0.
Para atribuciones legales completas (third-party software, datasets utilizados),
ver el archivo NOTICE.txt en este repositorio.
Contacto
- ๐ Web Mate: mate.ceroclawd.com
- ๐ Personal: gonzalorocca.com.ar
- ๐ง Email: gonn.nicolas@gmail.com
- ๐ผ LinkedIn: in/gonnicolas
- ๐ GitHub: @gonzalonicolasr
Mate es una IA. No reemplaza a nadie. Te acompaรฑa mientras laburรกs. Como un mate al lado de la pantalla โ cebado, listo, sin protagonismo.
- Downloads last month
- 142
4-bit