31 lines
1.0 KiB
Plaintext
31 lines
1.0 KiB
Plaintext
Convert-to-Quant (ctq) is installed for normal quantizations.
|
|
|
|
For quantizations and conversions, try:
|
|
|
|
- hf_to_nvfp4_gguf (Hugging Face to GGUF)
|
|
- gguf_to_nvfp4_gguf (GGUF to GGUF)
|
|
- safetensors_to_nvfp4_gguf (ComfyUI safetensors to GGUF)
|
|
- hf_to_nvfp4_safetensors (Hugging Face to ComfyUI safetensors)
|
|
- hf_to_nvfp4_hf (Hugging Face to NVFP4 Hugging Face)
|
|
- gguf_to_nvfp4_hf (GGUF to NVFP4 Hugging Face)
|
|
|
|
Depending on the source material.
|
|
|
|
hf cli command is also installed, eg you can:
|
|
|
|
|
|
hf download coder3101/gemma-4-12B-it-heretic --local-dir gemma-4-12B-it-heretic
|
|
hf_to_nvfp4_gguf -o gemma-4-12B-it-heretic_nvfp4 gemma-4-12B-it-heretic
|
|
|
|
The same directory can be quantized to NVFP4 Hugging Face format:
|
|
|
|
hf_to_nvfp4_hf -o gemma-4-12B-it-heretic-NVFP4-HF gemma-4-12B-it-heretic
|
|
|
|
Or to one ComfyUI NVFP4 safetensors file:
|
|
|
|
hf_to_nvfp4_safetensors -o gemma-4-12B-it-heretic-NVFP4.safetensors gemma-4-12B-it-heretic
|
|
|
|
A GGUF file can also be converted to NVFP4 Hugging Face format:
|
|
|
|
gguf_to_nvfp4_hf -o gemma-4-12B-it-heretic-NVFP4-HF gemma-4-12B-it-heretic.gguf
|