Edit model card

About

weighted/imatrix quants of https://huggingface.co/nitky/Megac4ai-command-r-plus

static quants are available at https://huggingface.co/mradermacher/Megac4ai-command-r-plus-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 35.1 for the desperate
GGUF i1-IQ1_M 38.3 mostly desperate
GGUF i1-IQ2_XXS 43.6
GGUF i1-IQ2_XS 48.3
PART 1 PART 2 i1-IQ2_S 50.9
PART 1 PART 2 i1-IQ2_M 55.2
PART 1 PART 2 i1-Q2_K 60.4 IQ3_XXS probably better
PART 1 PART 2 i1-IQ3_XXS 62.4 lower quality
PART 1 PART 2 i1-IQ3_XS 66.8
PART 1 PART 2 i1-Q3_K_S 70.3 IQ3_XS probably better
PART 1 PART 2 i1-IQ3_S 70.5 beats Q3_K*
PART 1 PART 2 i1-IQ3_M 73.1
PART 1 PART 2 i1-Q3_K_M 78.3 IQ3_S probably better
PART 1 PART 2 i1-Q3_K_L 85.2 IQ3_M probably better
PART 1 PART 2 i1-IQ4_XS 86.5
PART 1 PART 2 i1-Q4_0 91.5 fast, low quality
PART 1 PART 2 i1-Q4_K_S 91.8 optimal size/speed/quality
PART 1 PART 2 i1-Q4_K_M 96.7 fast, recommended
PART 1 PART 2 PART 3 i1-Q5_K_S 110.8
PART 1 PART 2 PART 3 i1-Q5_K_M 113.7
PART 1 PART 2 PART 3 i1-Q6_K 131.7 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
170
GGUF
+1
Unable to determine this model’s pipeline type. Check the docs .

Quantized from