mradermacher/ERNIE-21B-A3B-Claude-4.5-High-OPUS-Thinking-i1-GGUF

---

base_model: DavidAU/ERNIE-21B-A3B-Claude-4.5-High-OPUS-Thinking datasets:

• TeichAI/claude-4.5-opus-high-reasoning-250x

language:

• en

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

• mixture of experts
• moe
• 64 experts
• uncensored
• unsloth
• finetune
• All use cases
• bfloat16
• creative
• creative writing
• fiction writing
• plot generation
• sub-plot generation
• fiction writing
• story generation
• scene continue
• storytelling
• fiction story
• science fiction
• romance
• all genres
• story
• writing
• vivid prosing
• vivid writing
• fiction

---

About

weighted/imatrix quants of https://huggingface.co/DavidAU/ERNIE-21B-A3B-Claude-4.5-High-OPUS-Thinking

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

static quants are available at https://huggingface.co/mradermacher/ERNIE-21B-A3B-Claude-4.5-High-OPUS-Thinking-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	4.6	for the desperate
GGUF	i1-IQ1_M	5.1	mostly desperate
GGUF	i1-IQ2_XXS	5.9
GGUF	i1-IQ2_XS	6.6
GGUF	i1-IQ2_S	6.6
GGUF	i1-IQ2_M	7.3
GGUF	i1-Q2K_S	7.5	very low quality
GGUF	i1-Q2K	8.2	IQ3XXS probably better
GGUF	i1-IQ3_XXS	8.6	lower quality
GGUF	i1-IQ3_XS	9.1
GGUF	i1-Q3KS	9.6	IQ3XS probably better
GGUF	i1-IQ3S	9.6	beats Q3K*
GGUF	i1-IQ3_M	9.7
GGUF	i1-Q3KM	10.6	IQ3S probably better
GGUF	i1-Q3KL	11.5	IQ3M probably better
GGUF	i1-IQ4_XS	11.8
GGUF	i1-Q4_0	12.5	fast, low quality
GGUF	i1-Q4K_S	12.5	optimal size/speed/quality
GGUF	i1-Q4K_M	13.3	fast, recommended
GGUF	i1-Q4_1	13.8
GGUF	i1-Q5K_S	15.2
GGUF	i1-Q5K_M	15.6
GGUF	i1-Q6K	18.0	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.