Modelpublic

mradermacher/MultiVerse_70B-i1-GGUF

sourceHugging Faceotherupdated 2y agoView on Hugging Face

0likes588downloads

Model Card

weighted/imatrix quants of https://huggingface.co/MTSAIR/MultiVerse_70B

static quants are available at https://huggingface.co/mradermacher/MultiVerse_70B-GGUF

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.

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

Link	Type	Size/GB	Notes
GGUF	i1-IQ1_S	18.0	for the desperate
GGUF	i1-IQ1_M	19.3	mostly desperate
GGUF	i1-IQ2_XXS	21.5
GGUF	i1-IQ2_XS	23.5
GGUF	i1-IQ2_S	25.1
GGUF	i1-IQ2_M	26.9
GGUF	i1-Q2_K	28.6	IQ3_XXS probably better
GGUF	i1-IQ3_XXS	29.4	lower quality
GGUF	i1-IQ3_XS	31.5
GGUF	i1-IQ3_S	33.1	beats Q3_K*
GGUF	i1-Q3KS	33.1	IQ3_XS probably better
GGUF	i1-IQ3_M	34.8
GGUF	i1-Q3KM	36.8	IQ3_S probably better
GGUF	i1-Q3KL	40.1	IQ3_M probably better
GGUF	i1-IQ4_XS	40.4
GGUF	i1-Q4_0	42.7	fast, low quality
GGUF	i1-Q4KS	42.9	optimal size/speed/quality
GGUF	i1-Q4KM	45.3	fast, recommended
PART 1 PART 2	i1-Q5KS	51.5
PART 1 PART 2	i1-Q5KM	52.9
PART 1 PART 2	i1-Q6_K	60.9	practically like static Q6_K

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

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

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.