Edit model card

About

weighted/imatrix quants of https://huggingface.co/abacusai/TheProfessor-155b

static quants are available at https://huggingface.co/mradermacher/TheProfessor-155b-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 i1-IQ1_S 32.8 for the desperate
GGUF i1-IQ1_M 36.0 mostly desperate
GGUF i1-IQ2_XXS 41.3
GGUF i1-IQ2_XS 45.9
GGUF i1-IQ2_S 48.1
PART 1 PART 2 i1-IQ2_M 52.3
PART 1 PART 2 i1-Q2_K 57.1 IQ3_XXS probably better
PART 1 PART 2 i1-IQ3_XXS 60.6 lower quality
PART 1 PART 2 i1-Q3_K_XS 63.2
PART 1 PART 2 i1-IQ3_XS 63.3
PART 1 PART 2 i1-Q3_K_S 66.9 IQ3_XS probably better
PART 1 PART 2 i1-IQ3_S 67.1 beats Q3_K*
PART 1 PART 2 i1-IQ3_M 69.4
PART 1 PART 2 i1-Q3_K_M 74.7 IQ3_S probably better
PART 1 PART 2 i1-Q3_K_L 81.3 IQ3_M probably better
PART 1 PART 2 i1-IQ4_XS 82.8
PART 1 PART 2 i1-IQ4_NL 87.6 prefer IQ4_XS
PART 1 PART 2 i1-Q4_0 87.7 fast, low quality
PART 1 PART 2 i1-Q4_K_S 88.1 optimal size/speed/quality
PART 1 PART 2 i1-Q4_K_M 93.1 fast, recommended
PART 1 PART 2 PART 3 i1-Q5_K_S 106.7
PART 1 PART 2 PART 3 i1-Q5_K_M 109.6
PART 1 PART 2 PART 3 i1-Q6_K 127.2 practically like static Q6_K

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
7,002
GGUF
Model size
155B params
Architecture
llama
Unable to determine this model’s pipeline type. Check the docs .

Quantized from