mradermacher/Trinity-Large-TrueBase-i1-GGUF

---

base_model: arcee-ai/Trinity-Large-TrueBase language:

• en
• es
• fr
• de
• it
• pt
• ru
• ar
• hi
• ko
• zh

library_name: transformers license: apache-2.0 mradermacher: readme_rev: 1 quantized_by: mradermacher

---

About

weighted/imatrix quants of https://huggingface.co/arcee-ai/Trinity-Large-TrueBase

For a convenient overview and download list, visit our model page for this model.

static quants are available at https://huggingface.co/mradermacher/Trinity-Large-TrueBase-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	imatrix	0.6	imatrix file (for creating your own quants)
GGUF	i1-IQ1_S	79.0	for the desperate
GGUF	i1-IQ1_M	88.2	mostly desperate
GGUF	i1-IQ2_XXS	103.6
GGUF	i1-IQ2_XS	115.9
GGUF	i1-IQ2_S	116.4
GGUF	i1-IQ2_M	128.7
GGUF	i1-Q2K_S	132.0	very low quality
GGUF	i1-Q2K	144.9	IQ3XXS probably better
GGUF	i1-IQ3_XXS	153.1	lower quality
GGUF	i1-IQ3_XS	161.5
GGUF	i1-Q3KS	171.8	IQ3XS probably better
GGUF	i1-IQ3S	171.8	beats Q3K*
GGUF	i1-IQ3_M	172.3
GGUF	i1-Q3KM	189.4	IQ3S probably better
P1 P2 P3 P4 P5	i1-Q3KL	206.0	IQ3M probably better
P1 P2 P3 P4 P5	i1-IQ4_XS	212.2
P1 P2 P3 P4 P5	i1-Q4_0	224.8	fast, low quality
P1 P2 P3 P4 P5	i1-Q4K_S	225.0	optimal size/speed/quality
P1 P2 P3 P4 P5	i1-Q4K_M	239.7	fast, recommended
P1 P2 P3 P4 P5 P6	i1-Q4_1	249.5
P1 P2 P3 P4 P5 P6	i1-Q5KS	274.4
P1 P2 P3 P4 P5 P6	i1-Q5KM	282.2
P1 P2 P3 P4 P5 P6 P7	i1-Q6K	327.3	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.