AksaraLLM/aksarallm-1.5b-native-GGUF

aksarallm-1.5b-native-GGUF

GGUF quantizations of `AksaraLLM/aksarallm-1.5b-native` for inference with llama.cpp, Ollama, LM Studio, and other GGUF runtimes.

Files

CPU benchmark (AMD EPYC 7763, 2 threads, AVX2)

So a 2.04B model at q4km runs comfortably on a CPU laptop. Larger quants (q5km, q6k, q80) trade a bit of speed for better quality.

Quick start — llama.cpp

huggingface-cli download AksaraLLM/aksarallm-1.5b-native-GGUF aksarallm-1.5b-native.q4_k_m.gguf --local-dir .
./llama-cli -m aksarallm-1.5b-native.q4_k_m.gguf -p "Indonesia adalah" -n 64

Quick start — Ollama

huggingface-cli download AksaraLLM/aksarallm-1.5b-native-GGUF aksarallm-1.5b-native.q4_k_m.gguf Modelfile --local-dir .
ollama create aksara-aksarallm-1.5b-native -f Modelfile
ollama run aksara-aksarallm-1.5b-native "Lanjutkan: Indonesia adalah negara"

Source model

See `AksaraLLM/aksarallm-1.5b-native` for architecture, training data, eval results, and limitations.

Conversion provenance

• —Converted with `convert_hf_to_gguf.py` from llama.cpp
• —Quantized with llama-quantize from the same build
• —Architecture detected as llama
• —All files listed above are reproducible from the source HF safetensors

Note on the from-scratch model

This is a llama-3-style decoder built and trained from scratch by the AksaraLLM project. It does not use the Qwen2 ChatML template — it expects a plain ### Instruksi: ... ### Jawaban: ... style prompt (set up automatically by the included Modelfile).