About
weighted/imatrix quants of https://huggingface.co/bunnycore/Llama-3.2-3B-Stock
static quants are available at https://huggingface.co/mradermacher/Llama-3.2-3B-Stock-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 |
1.0 |
for the desperate |
GGUF |
i1-IQ1_M |
1.0 |
mostly desperate |
GGUF |
i1-IQ2_XXS |
1.1 |
|
GGUF |
i1-IQ2_XS |
1.2 |
|
GGUF |
i1-IQ2_S |
1.3 |
|
GGUF |
i1-IQ2_M |
1.3 |
|
GGUF |
i1-IQ3_XXS |
1.4 |
lower quality |
GGUF |
i1-Q2_K |
1.5 |
IQ3_XXS probably better |
GGUF |
i1-IQ3_XS |
1.6 |
|
GGUF |
i1-IQ3_S |
1.6 |
beats Q3_K* |
GGUF |
i1-Q3_K_S |
1.6 |
IQ3_XS probably better |
GGUF |
i1-IQ3_M |
1.7 |
|
GGUF |
i1-Q3_K_M |
1.8 |
IQ3_S probably better |
GGUF |
i1-Q3_K_L |
1.9 |
IQ3_M probably better |
GGUF |
i1-IQ4_XS |
1.9 |
|
GGUF |
i1-Q4_0_4_4 |
2.0 |
fast on arm, low quality |
GGUF |
i1-Q4_0_4_8 |
2.0 |
fast on arm+i8mm, low quality |
GGUF |
i1-Q4_0_8_8 |
2.0 |
fast on arm+sve, low quality |
GGUF |
i1-Q4_0 |
2.0 |
fast, low quality |
GGUF |
i1-Q4_K_S |
2.0 |
optimal size/speed/quality |
GGUF |
i1-Q4_K_M |
2.1 |
fast, recommended |
GGUF |
i1-Q5_K_S |
2.4 |
|
GGUF |
i1-Q5_K_M |
2.4 |
|
GGUF |
i1-Q6_K |
2.7 |
practically like static Q6_K |
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.