AMALIA is an open-source language model targeting European Portuguese, developed by a consortium of Portuguese universities and research centres and funded by the Government of Portugal. This is the SFT (supervised fine-tuned, instruction-following) variant. See the original model card and the technical report for full details.

Files

File	Quant	Size	Notes
`AMALIA-9B-0626-SFT-Q4_K_M.gguf`	Q4_K_M	~5.5 GB	4-bit, recommended balance of quality and size
`AMALIA-9B-0626-SFT-Q8_0.gguf`	Q8_0	~9.7 GB	8-bit, near-lossless

Converted with convert_hf_to_gguf.py (llama.cpp b8470) from the original bf16 weights to Q8_0; Q4_K_M requantized from the Q8_0 conversion (Q8_0 is near-lossless relative to bf16). The chat template (ChatML with the AMALIA Portuguese system prompt) is embedded in the GGUF metadata.

Usage

bash

# llama.cpp CLI (chat template is picked up automatically)
llama-cli -hf layerx-labs/AMALIA-9B-0626-SFT-GGUF:Q4_K_M

# or with a local file
llama-cli -m AMALIA-9B-0626-SFT-Q4_K_M.gguf -cnv

# OpenAI-compatible server
llama-server -m AMALIA-9B-0626-SFT-Q4_K_M.gguf -c 8192

License

Apache 2.0, same as the original model. All credit for the model goes to the AMALIA project.