Instructions to use magnitudedev/GLM-5.3-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 magnitudedev/GLM-5.3-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 magnitudedev/GLM-5.3-Flash-GGUF:NVFP4 # Run inference directly in the terminal: llama cli -hf magnitudedev/GLM-5.3-Flash-GGUF:NVFP4
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf magnitudedev/GLM-5.3-Flash-GGUF:NVFP4 # Run inference directly in the terminal: llama cli -hf magnitudedev/GLM-5.3-Flash-GGUF:NVFP4
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 magnitudedev/GLM-5.3-Flash-GGUF:NVFP4 # Run inference directly in the terminal: ./build/bin/llama cli -hf magnitudedev/GLM-5.3-Flash-GGUF:NVFP4
Use Docker
docker model run hf.co/magnitudedev/GLM-5.3-Flash-GGUF:NVFP4
- Llama new
- LM Studio
- Jan
- vLLM
How to use magnitudedev/GLM-5.3-Flash-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "magnitudedev/GLM-5.3-Flash-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": "magnitudedev/GLM-5.3-Flash-GGUF", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/magnitudedev/GLM-5.3-Flash-GGUF:NVFP4
- Ollama
How to use magnitudedev/GLM-5.3-Flash-GGUF with Ollama:
ollama run hf.co/magnitudedev/GLM-5.3-Flash-GGUF:NVFP4
- Unsloth Desktop
- Pi
How to use magnitudedev/GLM-5.3-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 magnitudedev/GLM-5.3-Flash-GGUF:NVFP4
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": "magnitudedev/GLM-5.3-Flash-GGUF:NVFP4" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use magnitudedev/GLM-5.3-Flash-GGUF with Docker Model Runner:
docker model run hf.co/magnitudedev/GLM-5.3-Flash-GGUF:NVFP4
- Lemonade
How to use magnitudedev/GLM-5.3-Flash-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull magnitudedev/GLM-5.3-Flash-GGUF:NVFP4
Run and chat with the model
lemonade run user.GLM-5.3-Flash-GGUF-NVFP4
List all available models
lemonade list
- Hermes Agent
How to use magnitudedev/GLM-5.3-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 magnitudedev/GLM-5.3-Flash-GGUF:NVFP4
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 magnitudedev/GLM-5.3-Flash-GGUF:NVFP4
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use magnitudedev/GLM-5.3-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 magnitudedev/GLM-5.3-Flash-GGUF:NVFP4
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 "magnitudedev/GLM-5.3-Flash-GGUF:NVFP4" \ --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"
GLM-5.3-Flash GGUF
GLM-5.3-Flash for Magnitude, in two variants, each lossless at its native size:
- FP8: Z.ai's release, the model exactly as trained.
- NVFP4: NVIDIA's 4-bit release, trained with quantization-aware distillation to hold the model's accuracy at 4 bits, at 57% of FP8's size.
Both keep the weights' separate scale tensors as released. llama.cpp doesn't support separate scale tensors, so it can't load these files; its own GGUFs of this model double the weights' size or round them.
Variants
| Variant | Source | Size |
|---|---|---|
| FP8 | zai-org/GLM-5.3-Flash at 46a050b |
327.2 GB |
| NVFP4 | nvidia/GLM-5.3-Flash-FP4-Local at 76348dd |
185.8 GB |
Both include the MTP layer for speculative decoding, as the text model's last block. Each is converted from its source and verified byte for byte against it.
Files
FP8/GLM-5.3-Flash-FP8-00001-of-00007.gguf ... -00007-of-00007.gguf
NVFP4/GLM-5.3-Flash-NVFP4-00001-of-00004.gguf ... -00004-of-00004.gguf
mmproj-BF16.gguf vision projector for FP8, as Z.ai ships it
mmproj-NVFP4.gguf vision projector for NVFP4, as NVIDIA ships it (part of its vision tower is quantized)
Point Magnitude at the first shard of a variant, and at its projector for image input.
Differences from llama.cpp GGUFs
llama.cpp's conversions of this model:
- BF16 doubles the size, and still isn't exact: a code times its scale can need more precision than BF16 holds.
- Q8_0, Q4_K and similar keep the size small but round every weight onto a new grid.
| Variant | How the weights are stored here |
|---|---|
| FP8 | Projections and routed experts: F8_E4M3 codes in X.weight, with one F32 scale per 128 x 128 tile in X.scale (Z.ai's weight_scale_inv). Everything else, output head included: BF16 and F32. |
| NVFP4 | NVIDIA's 4-bit codes with their block and tensor scales, in Magnitude's NVFP4 type. Tensors NVIDIA kept at 8 bits stay in their 8-bit forms with their scales. Everything else: BF16 and F32. |
Tensor names and metadata follow llama.cpp v0.9.0's
glm5-next converter.
License
MIT, as the source checkpoints.
- Downloads last month
- 424
4-bit
Model tree for magnitudedev/GLM-5.3-Flash-GGUF
Base model
zai-org/GLM-5.3-Flash