Edit model card

About

weighted/imatrix quants of https://huggingface.co/meta-llama/Meta-Llama-3.1-405B

static quants are available at https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-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
PART 1 PART 2 i1-IQ1_S 86.9 for the desperate
PART 1 PART 2 i1-IQ1_M 95.2 mostly desperate
PART 1 PART 2 PART 3 i1-IQ2_XXS 109.1
PART 1 PART 2 PART 3 i1-IQ2_XS 121.2
PART 1 PART 2 PART 3 i1-IQ2_S 127.5
PART 1 PART 2 PART 3 i1-IQ2_M 138.6
PART 1 PART 2 PART 3 PART 4 i1-Q2_K 151.3 IQ3_XXS probably better
PART 1 PART 2 PART 3 PART 4 i1-IQ3_XXS 157.8 lower quality
PART 1 PART 2 PART 3 PART 4 i1-IQ3_XS 168.2
PART 1 PART 2 PART 3 PART 4 i1-Q3_K_S 177.2 IQ3_XS probably better
PART 1 PART 2 PART 3 PART 4 i1-IQ3_S 177.7 beats Q3_K*
PART 1 PART 2 PART 3 PART 4 i1-IQ3_M 183.9
PART 1 PART 2 PART 3 PART 4 i1-Q3_K_M 197.6 IQ3_S probably better
P1 P2 P3 P4 P5 i1-Q3_K_L 215.3 IQ3_M probably better
P1 P2 P3 P4 P5 i1-IQ4_XS 219.2
P1 P2 P3 P4 P5 i1-Q4_0 232.2 fast, low quality
P1 P2 P3 P4 P5 i1-Q4_K_S 233.0 optimal size/speed/quality
P1 P2 P3 P4 P5 i1-Q4_K_M 245.8 fast, recommended
P1 P2 P3 P4 P5 P6 i1-Q5_K_S 282.3
P1 P2 P3 P4 P5 P6 i1-Q5_K_M 289.8
P1 P2 P3 P4 P5 P6 P7 i1-Q6_K 336.5 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. 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.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for mradermacher/Meta-Llama-3.1-405B-i1-GGUF

Finetuned
(12)
this model