Instructions to use hfsteady/Huihui-Flash-Next-Basalt-Vision-Overlay 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 hfsteady/Huihui-Flash-Next-Basalt-Vision-Overlay 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 hfsteady/Huihui-Flash-Next-Basalt-Vision-Overlay:BF16 # Run inference directly in the terminal: llama cli -hf hfsteady/Huihui-Flash-Next-Basalt-Vision-Overlay:BF16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf hfsteady/Huihui-Flash-Next-Basalt-Vision-Overlay:BF16 # Run inference directly in the terminal: llama cli -hf hfsteady/Huihui-Flash-Next-Basalt-Vision-Overlay:BF16
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 hfsteady/Huihui-Flash-Next-Basalt-Vision-Overlay:BF16 # Run inference directly in the terminal: ./build/bin/llama cli -hf hfsteady/Huihui-Flash-Next-Basalt-Vision-Overlay:BF16
Use Docker
docker model run hf.co/hfsteady/Huihui-Flash-Next-Basalt-Vision-Overlay:BF16
- Llama new
- LM Studio
- Jan
- Ollama
How to use hfsteady/Huihui-Flash-Next-Basalt-Vision-Overlay with Ollama:
ollama run hf.co/hfsteady/Huihui-Flash-Next-Basalt-Vision-Overlay:BF16
- Unsloth Desktop
- Pi
How to use hfsteady/Huihui-Flash-Next-Basalt-Vision-Overlay with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf hfsteady/Huihui-Flash-Next-Basalt-Vision-Overlay:BF16
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:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "hfsteady/Huihui-Flash-Next-Basalt-Vision-Overlay:BF16" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use hfsteady/Huihui-Flash-Next-Basalt-Vision-Overlay with Docker Model Runner:
docker model run hf.co/hfsteady/Huihui-Flash-Next-Basalt-Vision-Overlay:BF16
- Lemonade
How to use hfsteady/Huihui-Flash-Next-Basalt-Vision-Overlay with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull hfsteady/Huihui-Flash-Next-Basalt-Vision-Overlay:BF16
Run and chat with the model
lemonade run user.Huihui-Flash-Next-Basalt-Vision-Overlay-BF16
List all available models
lemonade list
- Hermes Agent
How to use hfsteady/Huihui-Flash-Next-Basalt-Vision-Overlay with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf hfsteady/Huihui-Flash-Next-Basalt-Vision-Overlay:BF16
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 hfsteady/Huihui-Flash-Next-Basalt-Vision-Overlay:BF16
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use hfsteady/Huihui-Flash-Next-Basalt-Vision-Overlay with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf hfsteady/Huihui-Flash-Next-Basalt-Vision-Overlay:BF16
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://127.0.0.1:8080/v1 \ --custom-model-id "hfsteady/Huihui-Flash-Next-Basalt-Vision-Overlay:BF16" \ --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"
Huihui Flash-Next: experimental Basalt vision overlay
This is a vision-only add-on, not a complete language model. Local assembly and file-integrity checks do not establish GPU runtime compatibility or image understanding quality. GPU validation, 262144-context image tests, and private Hermes image routing remain pending. Do not use private documents to validate it.
The projector is copied byte-for-byte, not requantized. Tokenizer metadata is converted to a metadata-only GGUF. Language tensors are not downloaded, changed, copied or uploaded by this overlay build. Full-pack conversion remains a separate fallback; neither approach automatically replaces the other.
Sources and pins
- Projector: official Huihui v2 GGUF repository,
revision
411f1f7349c9711e6f75aa8d20e1612eb3a4d55d, filemmproj-Qwen3.8-Flash-Next-BF16.gguf, 907543008 bytes, SHA256b1a82259702816a5330d7bd7607cd9676b11780e79ff7348c21103ff3ce49bd0. This is NOT the Swift projector. Upstream licensing and attribution apply. Its card declares Qwen Community License 1.0, but its LICENSE link was missing when assembled. The included LICENSE is fetched from the official Qwen base; its pinned source revision is recorded inlicense-source.json. - Text model: existing Basalt artifact,
revision
db74026775af2ee80366d4f6172b16f838b2a933. Seemanifest.jsonfor its exact size/SHA256 and runtime pins. - Basalt source: jesdga95/basalt,
commit
463d92e8edf18cf93839bf4cce541ddf7b073280. The loader hook is an experimental integration, not an upstream guarantee.
Contents and restore
manifest.json binds this overlay to the exact text pack's metadata digest,
size, image marker IDs and projector geometry. checksums.json records all
published file sizes/SHA256 values. The projector and tokenizer GGUF must remain
beside the manifest. No credentials, user prompts or private session data belong
in this repository.
- Restore and checksum-verify the existing text model and saved CUDA13/sm120 runtime on the GPU host, using the base artifact's restore instructions.
- Download this repository at a pinned commit into a separate directory.
Verify
checksums.jsonbefore installation. Keep the base model untouched. - Run
python install-vision-overlay.py --source /workspace/basalt-test/source. This backs up the Python loader and installs an opt-in hook only. - Start a separate test configuration with
server.vision="dynamic",262144context, INT8 KV and spec3. SetBASALT_VISION_OVERLAY_MANIFEST=/absolute/path/to/manifest.jsonfor that process only. The dynamic mode does not require the optional vision sidecar. - Verify synthetic image content via the authenticated private API; then check text/tools, long-context resource use and Hermes native-image routing.
Rollback: unset the environment variable and use the original text configuration. The installer does not start a server, alter the pack, provision a GPU, or publish an endpoint. Missing files, incorrect metadata, hashes or marker IDs fail closed. The base pack must still be independently SHA256-verified during restore; metadata matching alone does not validate every language tensor.
- Downloads last month
- 67
We're not able to determine the quantization variants.