About

static quants of https://huggingface.co/llmixer/BigAurelian-v0.5-120b-32k

weighted/imatrix quants are available at https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-i1-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 Q2_K 43.7
GGUF IQ3_XS 48.4
PART 1 PART 2 Q3_K_S 51.1
PART 1 PART 2 IQ3_S 51.3 beats Q3_K*
PART 1 PART 2 IQ3_M 53.0
PART 1 PART 2 Q3_K_M 57.0 lower quality
PART 1 PART 2 Q3_K_L 62.1
PART 1 PART 2 IQ4_XS 63.9
PART 1 PART 2 Q4_K_S 67.2 fast, recommended
PART 1 PART 2 Q4_K_M 71.0 fast, recommended
PART 1 PART 2 Q5_K_S 81.4
PART 1 PART 2 Q5_K_M 83.6
PART 1 PART 2 PART 3 Q6_K 97.0 very good quality
PART 1 PART 2 PART 3 Q8_0 125.5 fast, best quality

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.

Downloads last month
4
GGUF
Model size
118B params
Architecture
llama

2-bit

Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for mradermacher/BigAurelian-v0.5-120b-32k-GGUF

Quantized
(2)
this model