mradermacher/Qwen3-VL-8B-Instruct-Heretic-i1-GGUF

---

base_model: jKqfO84n/Qwen3-VL-8B-Instruct-Heretic language:

• en

library_name: transformers mradermacher: readme_rev: 1 quantized_by: mradermacher

---

About

weighted/imatrix quants of https://huggingface.co/jKqfO84n/Qwen3-VL-8B-Instruct-Heretic

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

static quants are available at https://huggingface.co/mradermacher/Qwen3-VL-8B-Instruct-Heretic-GGUF

This is a vision model - mmproj files (if any) will be in the static repository.

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	imatrix	0.1	imatrix file (for creating your own quants)
PART 1 PART 2	i1-IQ1_S	4.3	for the desperate
PART 1 PART 2	i1-IQ1_M	4.6	mostly desperate
PART 1 PART 2	i1-IQ2_XXS	5.1
PART 1 PART 2	i1-IQ2_XS	5.5
PART 1 PART 2	i1-IQ2_S	5.8
PART 1 PART 2	i1-IQ2_M	6.2
PART 1 PART 2	i1-Q2KS	6.3	very low quality
PART 1 PART 2	i1-Q2K	6.7	IQ3XXS probably better
PART 1 PART 2	i1-IQ3_XXS	6.8	lower quality
PART 1 PART 2	i1-IQ3_XS	7.4
PART 1 PART 2	i1-Q3KS	7.6	IQ3_XS probably better
PART 1 PART 2	i1-IQ3S	7.7	beats Q3K*
PART 1 PART 2	i1-IQ3_M	7.9
PART 1 PART 2	i1-Q3KM	8.3	IQ3_S probably better
PART 1 PART 2	i1-Q3KL	9.0	IQ3_M probably better
PART 1 PART 2	i1-IQ4_XS	9.2
PART 1 PART 2	i1-Q4_0	9.7	fast, low quality
PART 1 PART 2	i1-IQ4NL	9.7	prefer IQ4XS
PART 1 PART 2	i1-Q4KS	9.7	optimal size/speed/quality
PART 1 PART 2	i1-Q4KM	10.2	fast, recommended
PART 1 PART 2	i1-Q4_1	10.6
PART 1 PART 2	i1-Q5KS	11.5
PART 1 PART 2	i1-Q5KM	11.8
PART 1 PART 2	i1-Q6K	13.6	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.