mradermacher/Qwen3-MOE-2x8B-TNG-Deckard-Beta-16B-i1-GGUF

---

base_model: DavidAU/Qwen3-MOE-2x8B-TNG-Deckard-Beta-16B datasets:

• DavidAU/TNG-in-house-datasets
• DavidAU/PKD-in-house-datasets

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 40x
• creative
• all uses cases
• Jan-V1
• horror
• science fiction
• fantasy
• Star Trek
• finetune
• Deckard
• PKD
• thinking
• reasoning
• unsloth
• 2x8B
• moe
• mixture of experts
• merge

---

About

weighted/imatrix quants of https://huggingface.co/DavidAU/Qwen3-MOE-2x8B-TNG-Deckard-Beta-16B

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-2x8B-TNG-Deckard-Beta-16B-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	3.1	for the desperate
GGUF	i1-IQ1_M	3.4	mostly desperate
GGUF	i1-IQ2_XXS	3.9
GGUF	i1-IQ2_XS	4.2
GGUF	i1-IQ2_S	4.4
GGUF	i1-IQ2_M	4.8
GGUF	i1-Q2K_S	4.9	very low quality
GGUF	i1-Q2K	5.2	IQ3XXS probably better
GGUF	i1-IQ3_XXS	5.4	lower quality
GGUF	i1-IQ3_XS	5.8
GGUF	i1-Q3KS	6.0	IQ3XS probably better
GGUF	i1-IQ3S	6.1	beats Q3K*
GGUF	i1-IQ3_M	6.2
GGUF	i1-Q3KM	6.7	IQ3S probably better
GGUF	i1-Q3KL	7.2	IQ3M probably better
GGUF	i1-IQ4_XS	7.4
GGUF	i1-IQ4NL	7.8	prefer IQ4XS
GGUF	i1-Q4_0	7.8	fast, low quality
GGUF	i1-Q4K_S	7.8	optimal size/speed/quality
GGUF	i1-Q4K_M	8.2	fast, recommended
GGUF	i1-Q4_1	8.6
GGUF	i1-Q5K_S	9.4
GGUF	i1-Q5K_M	9.6
GGUF	i1-Q6K	11.1	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.