Instructions to use AngelSlim/Hy4-flash-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 AngelSlim/Hy4-flash-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 AngelSlim/Hy4-flash-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf AngelSlim/Hy4-flash-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 AngelSlim/Hy4-flash-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf AngelSlim/Hy4-flash-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 AngelSlim/Hy4-flash-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf AngelSlim/Hy4-flash-GGUF:Q4_K_M
Use Docker
docker model run hf.co/AngelSlim/Hy4-flash-GGUF:Q4_K_M
- Llama new
- LM Studio
- Jan
- Ollama
How to use AngelSlim/Hy4-flash-GGUF with Ollama:
ollama run hf.co/AngelSlim/Hy4-flash-GGUF:Q4_K_M
- Unsloth Desktop
- Pi
How to use AngelSlim/Hy4-flash-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf AngelSlim/Hy4-flash-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": "AngelSlim/Hy4-flash-GGUF:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use AngelSlim/Hy4-flash-GGUF with Docker Model Runner:
docker model run hf.co/AngelSlim/Hy4-flash-GGUF:Q4_K_M
- Lemonade
How to use AngelSlim/Hy4-flash-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull AngelSlim/Hy4-flash-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.Hy4-flash-GGUF-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use AngelSlim/Hy4-flash-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 AngelSlim/Hy4-flash-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 AngelSlim/Hy4-flash-GGUF:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use AngelSlim/Hy4-flash-GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf AngelSlim/Hy4-flash-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 "AngelSlim/Hy4-flash-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"
Mac patch is missing vision projector code (FIXED using mtmd hunks from Spark patch)
Hi, thanks for the Mac patch and the GGUFs! This is a really impressive model in my testing, and the quants you provided are perfect.
The README's Mac section builds 2cbca389f + hy4-flash-mac-minimal.patch, but that patch has no tools/mtmd changes. The hy_v4_flash projector type is unknown to that build, so the mmproj doesn't load and the llama-mtmd-cli image example fails on the Mac path (text works):
mtmd_get_memory_usage: error: Failed to load CLIP model from mmproj-Hy4-flash-bf16.gguf
srv load_model: [mtmd] failed to get memory usage of mmproj
The tools/mtmd hunks of hy4-flash-spark.patch apply cleanly on top of 2cbca389f + the Mac patch (6 files: CMakeLists.txt, clip-impl.h, clip.cpp, models/hy-v4-flash.cpp, models/models.h, mtmd.cpp):
awk '/^diff --git/{keep=($3 ~ /^a\/tools\/mtmd\//)} keep' hy4-flash-spark.patch > hy4-flash-mtmd.patch
git apply hy4-flash-mtmd.patch
With them, mmproj-Hy4-flash-bf16.gguf loads on an M5 Max 128 GB (441 tensors, about 1036 MiB on Metal). Folding these hunks into the Mac patch, or adding the step to the README, would get vision working on Mac.
Patch files used: hy4-flash-mac-minimal.patch sha256 97f1213f..., hy4-flash-spark.patch sha256 6ec50722....
I am opening a PR to this repo with the updated patch, if you'd like to use it!