mradermacher/Trixster-MoE-14B-A8B-v1-i1-GGUF

---

base_model: OccultAI/Trixster-MoE-14B-A8B-v1 datasets:

• cgato/SlimOrcaDedupCleaned
• Doctor-Shotgun/no-robots-sharegpt
• grimulkan/LimaRP-augmented
• lemonilia/LimaRP
• Locutusque/hercules-v5.0
• mlabonne/orpo-dpo-mix-40k
• mpasila/LimaRP-augmented-8k-context
• NobodyExistsOnTheInternet/PIPPAsharegptv2test
• NobodyExistsOnTheInternet/ToxicQAFinal
• OccultAI/Morpheus665
• Gryphe/Opus-WritingPrompts
• ResplendentAI/NSFWRPFormatDPO
• Sao10K/c2-Logs-Filtered
• Sao10K/Claude-3-Opus-Instruct-15K
• Sao10K/Short-Storygen-v2
• Setiaku/Stheno-v3.4-Instruct
• Setiaku/Stheno-3.4-Creative-2
• SicariusSicariiStuff/UBW_Tapestries
• Squish42/bluemoon-fandom-1-1-rp-cleaned
• teknium/OpenHermes-2.5
• Undi95/Capybara-ShareGPT
• Undi95/toxic-dpo-v0.1-sharegpt

language:

• en

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

• merge
• llama
• occult
• uncensored
• moe_karcher

---

About

weighted/imatrix quants of https://huggingface.co/OccultAI/Trixster-MoE-14B-A8B-v1

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

static quants are available at https://huggingface.co/mradermacher/Trixster-MoE-14B-A8B-v1-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	3.3	for the desperate
GGUF	i1-IQ1_M	3.5	mostly desperate
GGUF	i1-IQ2_XXS	4.0
GGUF	i1-IQ2_XS	4.3
GGUF	i1-IQ2_S	4.5
GGUF	i1-IQ2_M	4.9
GGUF	i1-Q2K_S	5.0	very low quality
GGUF	i1-Q2K	5.3	IQ3XXS probably better
GGUF	i1-IQ3_XXS	5.5	lower quality
GGUF	i1-IQ3_XS	5.9
GGUF	i1-Q3KS	6.2	IQ3XS probably better
GGUF	i1-IQ3S	6.2	beats Q3K*
GGUF	i1-IQ3_M	6.3
GGUF	i1-Q3KM	6.8	IQ3S probably better
GGUF	i1-Q3KL	7.3	IQ3M probably better
GGUF	i1-IQ4_XS	7.5
GGUF	i1-IQ4NL	8.0	prefer IQ4XS
GGUF	i1-Q4_0	8.0	fast, low quality
GGUF	i1-Q4K_S	8.0	optimal size/speed/quality
GGUF	i1-Q4K_M	8.4	fast, recommended
GGUF	i1-Q4_1	8.8
GGUF	i1-Q5K_S	9.6
GGUF	i1-Q5K_M	9.8
GGUF	i1-Q6K	11.3	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.