About
static quants of https://huggingface.co/fluently-lm/Llama-TI-8B-Instruct
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-TI-8B-Instruct-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 |
3.3 |
|
GGUF |
Q3_K_S |
3.8 |
|
GGUF |
Q3_K_M |
4.1 |
lower quality |
GGUF |
Q3_K_L |
4.4 |
|
GGUF |
IQ4_XS |
4.6 |
|
GGUF |
Q4_0_4_4 |
4.8 |
fast on arm, low quality |
GGUF |
Q4_K_S |
4.8 |
fast, recommended |
GGUF |
Q4_K_M |
5.0 |
fast, recommended |
GGUF |
Q5_K_S |
5.7 |
|
GGUF |
Q5_K_M |
5.8 |
|
GGUF |
Q6_K |
6.7 |
very good quality |
GGUF |
Q8_0 |
8.6 |
fast, best quality |
GGUF |
f16 |
16.2 |
16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
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.