mradermacher/Qwen3-MOE-6x6B-Star-Trek-Universe-Alpha-256k-ctx-36B-i1-GGUF

---

base_model: DavidAU/Qwen3-MOE-6x6B-Star-Trek-Universe-Alpha-256k-ctx-36B datasets:

• DavidAU/horror-nightmare1
• DavidAU/ST-Org
• DavidAU/ST-TNG
• DavidAU/ST-DS9
• DavidAU/ST-VOY
• DavidAU/ST-ENT
• DavidAU/ST-DIS

language:

• en

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

• programming
• code generation
• code
• coding
• coder
• chat
• code
• chat
• brainstorm
• qwen
• qwen3
• qwencoder
• brainstorm 20x
• creative
• all uses cases
• Jan-V1
• horror
• science fiction
• fantasy
• Star Trek
• Star Trek Original
• Star Trek The Next Generation
• Star Trek Deep Space Nine
• Star Trek Voyager
• Star Trek Enterprise
• Star Trek Discovery.
• finetune
• thinking
• reasoning
• unsloth
• 6x6B
• moe
• mixture of experts
• finetune

---

About

weighted/imatrix quants of https://huggingface.co/DavidAU/Qwen3-MOE-6x6B-Star-Trek-Universe-Alpha-256k-ctx-36B

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

static quants are available at https://huggingface.co/mradermacher/Qwen3-MOE-6x6B-Star-Trek-Universe-Alpha-256k-ctx-36B-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	0.1	imatrix file (for creating your own quants)
GGUF	i1-IQ1_S	5.7	for the desperate
GGUF	i1-IQ1_M	6.3	mostly desperate
GGUF	i1-IQ2_XXS	7.2
GGUF	i1-IQ2_XS	8.0
GGUF	i1-IQ2_S	8.2
GGUF	i1-IQ2_M	8.9
GGUF	i1-Q2K_S	9.2	very low quality
GGUF	i1-Q2K	9.9	IQ3XXS probably better
GGUF	i1-IQ3_XXS	10.4	lower quality
GGUF	i1-IQ3_XS	11.0
GGUF	i1-Q3KS	11.6	IQ3XS probably better
GGUF	i1-IQ3S	11.7	beats Q3K*
GGUF	i1-IQ3_M	11.9
GGUF	i1-Q3KM	12.9	IQ3S probably better
GGUF	i1-Q3KL	13.9	IQ3M probably better
GGUF	i1-IQ4_XS	14.3
GGUF	i1-Q4_0	15.2	fast, low quality
GGUF	i1-Q4K_S	15.2	optimal size/speed/quality
GGUF	i1-Q4K_M	16.2	fast, recommended
GGUF	i1-Q4_1	16.7
GGUF	i1-Q5K_S	18.4
GGUF	i1-Q5K_M	18.9
GGUF	i1-Q6K	21.8	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.