mradermacher/hydra-moe-120b-GGUF

About

static quants of https://huggingface.co/ibivibiv/hydra-moe-120b

weighted/imatrix quants are available at https://huggingface.co/mradermacher/hydra-moe-120b-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	41.6
GGUF	IQ3_XS	46.5
GGUF	Q3_K_S	49.1
GGUF	IQ3_S	49.2	beats Q3_K*
PART 1 PART 2	IQ3_M	50.1
PART 1 PART 2	Q3_K_M	54.5	lower quality
PART 1 PART 2	Q3_K_L	59.1
PART 1 PART 2	IQ4_XS	61.3
PART 1 PART 2	Q4_K_S	64.7	fast, recommended
PART 1 PART 2	Q4_K_M	68.8	fast, recommended
PART 1 PART 2	Q5_K_S	78.3
PART 1 PART 2	Q5_K_M	80.7
PART 1 PART 2	Q6_K	93.3	very good quality
PART 1 PART 2 PART 3	Q8_0	120.9	fast, best quality

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.