Instructions to use Blugart/estragon-9b-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Blugart/estragon-9b-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 Blugart/estragon-9b-gguf:Q4_K_M # Run inference directly in the terminal: llama cli -hf Blugart/estragon-9b-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 Blugart/estragon-9b-gguf:Q4_K_M # Run inference directly in the terminal: llama cli -hf Blugart/estragon-9b-gguf:Q4_K_M
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf Blugart/estragon-9b-gguf:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf Blugart/estragon-9b-gguf:Q4_K_M
Use Docker
docker model run hf.co/Blugart/estragon-9b-gguf:Q4_K_M
- Llama new
- LM Studio
- Jan
- vLLM
How to use Blugart/estragon-9b-gguf with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Blugart/estragon-9b-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": "Blugart/estragon-9b-gguf", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Blugart/estragon-9b-gguf:Q4_K_M
- Ollama
How to use Blugart/estragon-9b-gguf with Ollama:
ollama run hf.co/Blugart/estragon-9b-gguf:Q4_K_M
- Unsloth Desktop
- Pi
How to use Blugart/estragon-9b-gguf with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Blugart/estragon-9b-gguf:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "Blugart/estragon-9b-gguf:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use Blugart/estragon-9b-gguf with Docker Model Runner:
docker model run hf.co/Blugart/estragon-9b-gguf:Q4_K_M
- Lemonade
How to use Blugart/estragon-9b-gguf with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Blugart/estragon-9b-gguf:Q4_K_M
Run and chat with the model
lemonade run user.estragon-9b-gguf-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use Blugart/estragon-9b-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 Blugart/estragon-9b-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://127.0.0.1:9931/v1 hermes config set model.default Blugart/estragon-9b-gguf:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use Blugart/estragon-9b-gguf with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Blugart/estragon-9b-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://127.0.0.1:9931/v1 \ --custom-model-id "Blugart/estragon-9b-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"
Estragon-9B — GGUF
GGUF quantizations of Estragon-9B, a Godot 4.7 / GDScript specialist (Qwen3.5-9B fine-tuned with SFT + GRPO using a headless-Godot judge as reward). Full model card, benchmarks, and method: bf16 repo · GitHub (harness, eval sets, ADRs).
Which file?
Every quant was run through the full 300-task GDScript-Eval v2 (headless Godot 4.7 as judge, greedy pass@1, deployment system prompt) — the quantization cost is measured, not guessed:
| file | bits | size | gdeval_v2 | vs bf16 (248/300) |
|---|---|---|---|---|
| estragon-9b-Q5_K_M.gguf | 5-bit | 6.5 GB | 249/300 (83.0%) | +1 — statistically identical to bf16. Recommended. |
| estragon-9b-Q8_0.gguf | 8-bit | 9.5 GB | 248/300 (82.7%) | ±0 — indistinguishable from bf16 |
| estragon-9b-Q4_K_M.gguf | 4-bit | 5.6 GB | 229/300 (76.3%) | −19 — the 8 GB VRAM pick; API-precision degrades most |
SHA-256:
6803c3c115bdd4a5de2f54e860107cb8b7b384443f7a4e97eced1160c2415281 estragon-9b-Q4_K_M.gguf
db10164493835e3039b1cc4d931fd1e9e22b1c8dd99a4e34b52ab8968b51785d estragon-9b-Q5_K_M.gguf
5acbb583d451e4486618faaf95d424fbc3a3d5b70dc0604492054e8c8e0be0cd estragon-9b-Q8_0.gguf
Ollama
ollama run hf.co/Blugart/estragon-9b-gguf:Q5_K_M --think=false "A 2D platformer jump with coyote time, CharacterBody2D"
⚠️ Pass --think=false (API: "think": false). Ollama's qwen3.5 runtime
manages <think> blocks itself and there is currently no model-level way to
disable it (ollama#14617).
Estragon is a non-thinking fine-tune: without the flag it burns tokens on
reasoning and measured −15 tasks on the 300-task eval.
This repo ships template, system, and params files, so Ollama picks up
the chat template, the deployment system prompt, and the recommended sampling
parameters automatically. Alternatively, download a GGUF and use the included
Modelfile:
ollama create estragon -f Modelfile
ollama run estragon --think=false "..."
llama.cpp
llama-server -m estragon-9b-Q5_K_M.gguf -ngl 99 --port 8080 \
--chat-template-kwargs '{"enable_thinking":false}'
⚠️ enable_thinking:false is required. The embedded Qwen3.5 chat template
otherwise opens a reasoning block; this is a non-thinking fine-tune and will
produce empty or degraded answers with thinking enabled (measured: −15 tasks,
and unclosed think blocks eat the whole token budget).
The system prompt is part of the model — all numbers were measured with
it (see the system file in this repo, or the full card). Recommended
sampling: temperature 0.7, top_p 0.8, top_k 20; do not enable
reasoning/thinking mode.
License
Apache 2.0 (inherited from Qwen3.5-9B).
- Downloads last month
- 1,383
4-bit
5-bit
8-bit