gemma-2b-GGUF/README.md

base_model, extra_gated_button_content, extra_gated_heading, extra_gated_prompt, language, library_name, license, quantized_by

base_model	extra_gated_button_content	extra_gated_heading	extra_gated_prompt	language	library_name	license	quantized_by
google/gemma-2b	Acknowledge license	Access Gemma on Hugging Face	To access Gemma on Hugging Face, you’re required to review and agree to Google’s usage license. To do this, please ensure you’re logged-in to Hugging Face and click below. Requests are processed immediately.	en	transformers	gemma	mradermacher

About

static quants of https://huggingface.co/google/gemma-2b

weighted/imatrix quants are available at https://huggingface.co/mradermacher/gemma-2b-i1-GGUF

Usage

If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files.

Provided Quants

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Link	Type	Size/GB	Notes
GGUF	Q2_K	1.3
GGUF	Q3_K_S	1.4
GGUF	Q3_K_M	1.5	lower quality
GGUF	Q3_K_L	1.6
GGUF	IQ4_XS	1.6
GGUF	Q4_0_4_4	1.7	fast on arm, low quality
GGUF	Q4_K_S	1.7	fast, recommended
GGUF	Q4_K_M	1.7	fast, recommended
GGUF	Q5_K_S	1.9
GGUF	Q5_K_M	1.9
GGUF	Q6_K	2.2	very good quality
GGUF	Q8_0	2.8	fast, best quality
GGUF	f16	5.1	16 bpw, overkill

Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):

And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9

FAQ / Model Request

See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized.

Thanks

I thank my company, nethype GmbH, for letting me use its servers and providing upgrades to my workstation to enable this work in my free time.