mradermacher's picture
auto-patch README.md
15cd4c3 verified
|
raw
history blame
4.14 kB
metadata
base_model: []
language:
  - en
library_name: transformers
license: other
quantized_by: mradermacher
tags:
  - mergekit
  - merge

About

weighted/imatrix quants of https://huggingface.co/sophosympatheia/Midnight-Miqu-103B-v1.0

static quants are available at https://huggingface.co/mradermacher/Midnight-Miqu-103B-v1.0-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-IQ2_M 35.1
GGUF i1-Q2_K 38.3 IQ3_XXS probably better
GGUF i1-IQ3_XXS 40.0 fast, lower quality
GGUF i1-IQ3_XS 42.5
GGUF i1-Q3_K_S 44.9 IQ3_XS probably better
PART 1 PART 2 i1-Q3_K_M 50.0 IQ3_S probably better
PART 1 PART 2 i1-Q3_K_L 54.5 IQ3_M probably better
PART 1 PART 2 i1-Q4_K_S 59.0 optimal size/speed/quality
PART 1 PART 2 i1-Q4_K_M 62.3 fast, medium quality
PART 1 PART 2 i1-Q5_K_S 71.4
PART 1 PART 2 i1-Q5_K_M 73.3
PART 1 PART 2 i1-Q6_K 85.1 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