🧠 Granite 4.0 H Small Heretic GGUFs
Quantized version of: pszemraj/granite-4.0-h-small-heretic_hi
📦 Available GGUFs
| Format | Description |
|---|---|
| F16 | Full precision (16-bit), better quality, larger size ⚖️ |
| Q4_K_XL | Quantized (4-bit XL variant, based on the quantization table of the unsloth model granite-4.0-h-small), smaller size, faster inference ⚡ |
🚀 Usage
Example with llama.cpp:
./main -m ./gguf-file-name.gguf -p "Hello world!"
- Downloads last month
- 31
Hardware compatibility
Log In to add your hardware
4-bit
16-bit
Model tree for rodrigomt/granite-4.0-h-small-heretic-high-GGUF
Base model
pszemraj/granite-4.0-h-small-heretic_hi