How to use from
llama.cppInstall from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf vnyaryan/playwright1model_q4_k_m:Q4_K_M# Run inference directly in the terminal:
llama cli -hf vnyaryan/playwright1model_q4_k_m:Q4_K_MUse 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 vnyaryan/playwright1model_q4_k_m:Q4_K_M# Run inference directly in the terminal:
./llama-cli -hf vnyaryan/playwright1model_q4_k_m:Q4_K_MBuild 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 vnyaryan/playwright1model_q4_k_m:Q4_K_M# Run inference directly in the terminal:
./build/bin/llama-cli -hf vnyaryan/playwright1model_q4_k_m:Q4_K_MUse Docker
docker model run hf.co/vnyaryan/playwright1model_q4_k_m:Q4_K_MQuick Links
Uploaded model
- Developed by: vnyaryan
- License: apache-2.0
- Finetuned from model : unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
🧠 Playwright Command Bot (Fine-Tuned with Unsloth + LoRA)
This model was fine-tuned by @vnyaryan using Unsloth on a ShareGPT-style dataset with command references for browser automation.
🚀 Capabilities
- Understands and returns commands like
goto_url,click,input_detail - Instruction-following tuned on
mcp_commands_sharegpt.jsonl - Exported in GGUF format for Llama.cpp-based inference
🧩 Example Prompt
- Downloads last month
- 16
Hardware compatibility
Log In to add your hardware
4-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Install (macOS, Linux)
# Start a local OpenAI-compatible server with a web UI: llama serve -hf vnyaryan/playwright1model_q4_k_m:Q4_K_M# Run inference directly in the terminal: llama cli -hf vnyaryan/playwright1model_q4_k_m:Q4_K_M