About

weighted/imatrix quants of https://huggingface.co/OpenMOSE/Qwen3-VL-REAP-145B-A22B

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-REAP-145B-A22B-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
GGUF	imatrix	0.4	imatrix file (for creating your own qwuants)
GGUF	i1-IQ1_S	29.8	for the desperate
GGUF	i1-IQ1_M	33.0	mostly desperate
GGUF	i1-IQ2_XXS	38.2
GGUF	i1-IQ2_XS	42.5
GGUF	i1-IQ2_S	43.6
GGUF	i1-IQ2_M	47.8
GGUF	i1-Q2_K_S	49.3	very low quality
PART 1 PART 2	i1-Q2_K	53.0	IQ3_XXS probably better
PART 1 PART 2	i1-IQ3_XXS	55.8	lower quality
PART 1 PART 2	i1-IQ3_XS	59.2
PART 1 PART 2	i1-Q3_K_S	62.6	IQ3_XS probably better
PART 1 PART 2	i1-IQ3_S	62.6	beats Q3_K*
PART 1 PART 2	i1-IQ3_M	63.7
PART 1 PART 2	i1-Q3_K_M	69.4	IQ3_S probably better
PART 1 PART 2	i1-Q3_K_L	75.2	IQ3_M probably better
PART 1 PART 2	i1-IQ4_XS	77.2
PART 1 PART 2	i1-Q4_0	82.0	fast, low quality
PART 1 PART 2	i1-Q4_K_S	82.4	optimal size/speed/quality
PART 1 PART 2	i1-Q4_K_M	87.5	fast, recommended
PART 1 PART 2	i1-Q4_1	90.7
PART 1 PART 2 PART 3	i1-Q5_K_S	99.7
PART 1 PART 2 PART 3	i1-Q5_K_M	102.7
PART 1 PART 2 PART 3	i1-Q6_K	118.8	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

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.