mradermacher/grok-1-GGUF

About

static quants of https://huggingface.co/xai-org/grok-1

Made possible by Arki05, keyfan, v2ray and many others. See https://github.com/ggerganov/llama.cpp/issues/6120

Initial quants are lower quality than theoretically possible.

weighted/imatrix quants are available at https://huggingface.co/mradermacher/grok-1-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
PART 1 PART 2 PART 3	Q2_K	117.2
PART 1 PART 2 PART 3	IQ3_XS	130.7
PART 1 PART 2 PART 3	IQ3_S	138.5	beats Q3_K*
PART 1 PART 2 PART 3	Q3_K_S	138.5
PART 1 PART 2 PART 3 PART 4	IQ3_M	145.3
PART 1 PART 2 PART 3 PART 4	Q3_K_M	153.0	lower quality
PART 1 PART 2 PART 3 PART 4	Q3_K_L	164.5
PART 1 PART 2 PART 3 PART 4	IQ4_XS	172.3
PART 1 PART 2 PART 3 PART 4	Q4_0	179.7	fast, low quality
PART 1 PART 2 PART 3 PART 4	IQ4_NL	181.6	prefer IQ4_XS
PART 1 PART 2 PART 3 PART 4	Q4_K_S	181.6	fast, recommended
PART 1 PART 2 PART 3 PART 4	Q4_K_M	193.3	fast, recommended
P1 P2 P3 P4 P5	Q5_K_S	219.1
P1 P2 P3 P4 P5	Q5_K_M	225.9
P1 P2 P3 P4 P5 P6	Q6_K	260.9	very good quality
P1 P2 P3 P4 P5 P6 P7	Q8_0	337.1	fast, best quality
P1 P2 P3 P4 P5 P6 P7 P8 P9 P10 P11 P12 P13 P14 P15 P16	SOURCE	633.1	source gguf, only provided when it was hard to come by

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.