8-bit (Q8_0) GGUF quantization of lapa-llm/lapa-v0.1.3-instruct — a Ukrainian-specialized instruction model built on Google's Gemma 3 12B, with roughly 80 000 of its 256 000 tokenizer tokens replaced by Ukrainian-oriented ones.

This repository contains only the quantized weights. For the original model, tokenizer sources, training details and intended use, see the upstream model card.

Q8_0 is the highest-fidelity common GGUF quant (8-bit, ~0.5 GB per B params). It keeps generation quality effectively indistinguishable from the bf16 original while roughly halving memory, so the full 12B model fits comfortably on one 24 GB card (e.g. RTX 3090/4090) with room for KV cache. This matters here because Lapa's modified tokenizer makes the model sensitive to precision loss — lower-bit quants (Q4/Q5/Q6) risk degrading Ukrainian morphology, so Q8_0 is the recommended operating point.

Following the official Lapa quantization recipe, which uses a patched converter that preserves Lapa's custom tokenizer (tokenizer.model + merge_info.json) so no vocabulary precision is lost:

Derived from Google Gemma 3 and inherits the Gemma Terms of Use. Use of these weights is subject to those terms and to any terms of the upstream lapa-llm/lapa-v0.1.3-instruct model.