Instructions to use ramosvs/zest with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ramosvs/zest with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ramosvs/zest",
	filename="zest-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 ramosvs/zest with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ramosvs/zest:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf ramosvs/zest:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ramosvs/zest:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf ramosvs/zest: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 ramosvs/zest:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ramosvs/zest: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 ramosvs/zest:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ramosvs/zest:Q4_K_M

Use Docker

docker model run hf.co/ramosvs/zest:Q4_K_M

LM Studio
Jan

vLLM

How to use ramosvs/zest with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ramosvs/zest:Q4_K_M

Ollama
How to use ramosvs/zest with Ollama:
```
ollama run hf.co/ramosvs/zest:Q4_K_M
```

Unsloth Studio

How to use ramosvs/zest 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 ramosvs/zest 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 ramosvs/zest to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ramosvs/zest to start chatting

How to use ramosvs/zest with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf ramosvs/zest: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": "ramosvs/zest:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use ramosvs/zest with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf ramosvs/zest: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 ramosvs/zest:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use ramosvs/zest with Docker Model Runner:
```
docker model run hf.co/ramosvs/zest:Q4_K_M
```

Lemonade

How to use ramosvs/zest with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ramosvs/zest:Q4_K_M

Run and chat with the model

lemonade run user.zest-Q4_K_M

List all available models

lemonade list

Zest — Local AI Compression Model for Squeezr

Zest is a fine-tuned 0.8B model that compresses coding tool outputs (bash, git, test runners, file reads) to save context window tokens. Designed to run locally via Ollama as the AI backend for Squeezr.

Quick install

# Install via Squeezr wizard (recommended)
squeezr zest

Or manually:

ollama pull ramosvs/zest  # coming soon
# Or use the GGUF directly:
ollama create zest -f Modelfile.zest

What it does

Input: raw coding tool output (git diff, npm install, test failure, file read...)
Output: compressed version preserving errors, paths, function names, key values
Typical savings: 52–72% on real Claude Code tool outputs (>5K chars)
Minimum input: 1500 chars (smaller inputs may expand — handled by Squeezr's safety net)

Performance

Training

Fine-tuned from Qwen3.5-0.8B using LoRA (r=16, α=32) on a distillation dataset of 1,111 training pairs generated by Claude Opus 4.7. Dataset covers 50+ categories: git, test runners, build tools, docker, kubectl, npm, stack traces, MCP responses, etc.

Usage with Ollama

FROM zest-Q4_K_M.gguf
SYSTEM \"\"\"You are compressing a coding tool output to save tokens. Extract ONLY what is essential: errors, file paths, function names, test failures, key values, warnings. Be extremely concise, target under 150 tokens. Output only the compressed content, nothing else.\"\"\"
PARAMETER temperature 0
PARAMETER top_p 1
PARAMETER top_k 1
PARAMETER num_predict 300
PARAMETER num_ctx 2048

Integration with Squeezr

After squeezr zest configures everything, add to ~/.squeezr/squeezr.toml:

[compression]
ai_compression = true
ai_min_chars = 1500
[local]
enabled = true
upstream_url = "http://localhost:11434"
compression_model = "zest"

Downloads last month: 48

GGUF

Model size

0.8B params

Architecture

qwen35

Hardware compatibility

4-bit

Model tree for ramosvs/zest

Base model

Qwen/Qwen2.5-0.5B

Finetuned

Qwen/Qwen2.5-0.5B-Instruct

Quantized

(224)

this model