mradermacher/BigWeave-v13-90b-i1-GGUF

---

base_model: llmixer/BigWeave-v13-90b language:

• en

library_name: transformers quantized_by: mradermacher tags:

• mergekit
• merge

---

About

weighted/imatrix quants of https://huggingface.co/llmixer/BigWeave-v13-90b

static quants are available at https://huggingface.co/mradermacher/BigWeave-v13-90b-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	i1-IQ1_S	18.5	for the desperate
GGUF	i1-IQ1_M	20.3	mostly desperate
GGUF	i1-IQ2_XXS	23.3
GGUF	i1-IQ2_XS	25.9
GGUF	i1-IQ2_S	27.2
GGUF	i1-IQ2_M	29.6
GGUF	i1-Q2K	32.4	IQ3XXS probably better
GGUF	i1-IQ3_XXS	33.8	lower quality
GGUF	i1-IQ3_XS	36.0
GGUF	i1-Q3KS	37.9	IQ3XS probably better
GGUF	i1-IQ3S	38.0	beats Q3K*
GGUF	i1-IQ3_M	39.3
GGUF	i1-Q3KM	42.3	IQ3S probably better
GGUF	i1-Q3KL	46.1	IQ3M probably better
GGUF	i1-IQ4_XS	47.0
GGUF	i1-Q4_0	49.7	fast, low quality
GGUF	i1-Q4K_S	49.9	optimal size/speed/quality
PART 1 PART 2	i1-Q4KM	52.7	fast, recommended
PART 1 PART 2	i1-Q5KS	60.5
PART 1 PART 2	i1-Q5KM	62.1
PART 1 PART 2	i1-Q6K	72.1	practically like static Q6K

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

!image.png

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. Additional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.