---
base_model: google/gemma-3-1b-it
tags:
- gemma3
- instruct
- 32k context
- all use cases
- maxed quants
- Neo Imatrix
license: apache-2.0
---

(quants uploading, examples to be added)

<h2>Gemma-3-1b-it-MAX-NEO-Imatrix-GGUF</h2>

Google's newest Gemma-3 model with Neo Imatrix and Maxed out quants.

Recommend quants IQ3s / IQ4XS / Q4s for best results for creative.

Recommend q5s/q6/q8 for general usage.

Q8 is a maxed quant only, as imatrix has no effect on this quant.

Note that IQ1 performance is low, whereas IQ2s are passable.

"MAXED"

This means the embed and output tensor are set at "BF16" (full precision) for all quants.

This enhances quality, depth and general performance at the cost of a slightly larger quant.

"NEO IMATRIX"

A strong, in house built, imatrix dataset built by David_AU.

- more to follow -