You can deploy this model and start earning money today!

x1nx3r/
Llama-3.2-3B-thinking-v3-13.9K-GGUF

Name: Llama-3.2-3B-thinking-v3-13.9K-GGUF
Availability: InStock

Views

No views yet

output_sft GGUF

This folder contains a float16 GGUF export of the output_sft fine-tuned Llama-3.2-3B-Instruct model along with the tokenizer assets required for Hugging Face uploads.

Files

output_sft-f16.gguf – converted weights (float16)
config.json – original Hugging Face config for reference
tokenizer.json, tokenizer_config.json, special_tokens_map.json, generation_config.json – tokenizer and generation settings

Usage

./llama-b7083-bin-ubuntu-x64/bin/llama-cli \
  -m output_sft-f16.gguf \
  -p "Hello, world!"

When uploading to Hugging Face, include these files and add a model card describing the fine-tuning data and license.

x1nx3r/Llama-3.2-3B-thinking-v3-13.9K-GGUF

output_sft GGUF

Files

Usage

x1nx3r/
Llama-3.2-3B-thinking-v3-13.9K-GGUF