Question 1

What is 1bit-MONSTER/gemma-2-2b-it-GGUF?

Accepted Answer

--- license: gemma base_model: - google/gemma-2-2b-it tags: - gguf --- # gemma-2-2b-it — GGUF (Q4_K_M) bartowski's Q4_K_M GGUF, re-hosted with measured performance for the [1bit engine](https://github.com/1bit-MONSTER/engine) on Strix Halo. Licensed under [Google's Gemma Terms of Use](https://ai.google.dev/gemma/terms). ## Contents - `gemma-2-2b-it-Q4_K_M.gguf` ## Measured performance (Strix Halo, Vulkan) pp512: 2429 tok/s · tg128: 39.4 tok/s ## Running it ```bash 1bit serve -m gemma-2-2b-it-Q4_K_M.gguf --device vulkan ``` ## Attribution - Base model: [google/gemma-2-2b-it](https://huggingface.co/google/gemma-2-2b-it). - Quantization: [bartowski/gemma-2-2b-it-GGUF](https://huggingface.co/bartowski/gemma-2-2b-it-GGUF).

Question 2

What license applies to 1bit-MONSTER/gemma-2-2b-it-GGUF?

Accepted Answer

License: gemma. Verify terms on Hugging Face before commercial use.

Question 3

How do I run 1bit-MONSTER/gemma-2-2b-it-GGUF locally?

Accepted Answer

Download a GGUF file from this page and load it in guIDE or llama.cpp. Pipeline task: text-generation.

Question 4

How much VRAM or disk space does 1bit-MONSTER/gemma-2-2b-it-GGUF need?

Accepted Answer

Runs locally from ~1.59 GB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

1bit-MONSTER/gemma-2-2b-it-GGUF overview

Repository Files & Downloads

Model Details

Model README

gemma-2-2b-it — GGUF (Q4_K_M)

Contents

Measured performance (Strix Halo, Vulkan)

Running it

Attribution

Run 1bit-MONSTER/gemma-2-2b-it-GGUF with guIDE

Model ID	1bit-MONSTER/gemma-2-2b-it-GGUF
Author	1bit-MONSTER
Pipeline	—
License	gemma
Base model	google/gemma-2-2b-it
Last modified	2026-09-26T15:11:57.000Z