tamilan-2-27b-GGUF / README.md
mradermacher's picture
auto-patch README.md
1c6d9fc verified
|
raw
history blame
3.49 kB
metadata
base_model: mervinpraison/tamilan-2-27b
language:
  - en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - gemma2
  - trl
  - sft
  - praisonai
  - praison

About

static quants of https://huggingface.co/mervinpraison/tamilan-2-27b

weighted/imatrix quants are available at https://huggingface.co/mradermacher/tamilan-2-27b-i1-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 Q2_K 10.5
GGUF IQ3_XS 11.7
GGUF IQ3_S 12.3 beats Q3_K*
GGUF Q3_K_S 12.3
GGUF IQ3_M 12.6
GGUF Q3_K_M 13.5 lower quality
GGUF Q3_K_L 14.6
GGUF IQ4_XS 15.0
GGUF Q4_K_S 15.8 fast, recommended
GGUF Q4_K_M 16.7 fast, recommended
GGUF Q5_K_S 19.0
GGUF Q5_K_M 19.5
GGUF Q6_K 22.4 very good quality
GGUF Q8_0 29.0 fast, best quality

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.