mradermacher's picture
auto-patch README.md
78d82a8 verified
metadata
base_model: chargoddard/llama3-42b-v0
datasets:
  - JeanKaddour/minipile
language:
  - en
library_name: transformers
license: llama3
quantized_by: mradermacher
tags:
  - axolotl
  - mergekit
  - llama

About

weighted/imatrix quants of https://huggingface.co/chargoddard/llama3-42b-v0

static quants are available at https://huggingface.co/mradermacher/llama3-42b-v0-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 9.7 for the desperate
GGUF i1-IQ1_M 10.6 mostly desperate
GGUF i1-IQ2_XXS 12.0
GGUF i1-IQ2_XS 13.2
GGUF i1-IQ2_S 13.9
GGUF i1-IQ2_M 15.0
GGUF i1-Q2_K 16.4 IQ3_XXS probably better
GGUF i1-IQ3_XXS 17.0 lower quality
GGUF i1-IQ3_XS 18.2
GGUF i1-Q3_K_S 19.1 IQ3_XS probably better
GGUF i1-IQ3_S 19.1 beats Q3_K*
GGUF i1-IQ3_M 19.7
GGUF i1-Q3_K_M 21.1 IQ3_S probably better
GGUF i1-Q3_K_L 22.9 IQ3_M probably better
GGUF i1-IQ4_XS 23.4
GGUF i1-Q4_0 24.8 fast, low quality
GGUF i1-Q4_K_S 24.8 optimal size/speed/quality
GGUF i1-Q4_K_M 26.2 fast, recommended
GGUF i1-Q5_K_S 29.9
GGUF i1-Q5_K_M 30.7
GGUF i1-Q6_K 35.5 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.