language:
- en
library_name: transformers
quantized_by: mradermacher
source_fix: convert --vocab-type bpe --pad-vocab
About
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
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 |
|---|---|---|---|
| PART 1 PART 2 | Q2_K | 51.6 | |
| PART 1 PART 2 | IQ3_S | 59.6 | beats Q3_K* |
| PART 1 PART 2 | Q3_K_S | 59.6 | |
| PART 1 PART 2 | Q3_K_M | 66.3 | lower quality |
| PART 1 PART 2 | Q3_K_L | 72.1 | |
| PART 1 PART 2 | Q4_0 | 76.5 | |
| PART 1 PART 2 | Q4_K_S | 77.0 | fast, recommended |
| PART 1 PART 2 | Q4_K_M | 81.4 | fast, recommended |
| PART 1 PART 2 | Q5_K_S | 92.3 | |
| PART 1 PART 2 | Q5_K_M | 94.9 | |
| PART 1 PART 2 PART 3 | Q6_K | 109.2 | very good quality |
| PART 1 PART 2 PART 3 | Q8_0 | 139.9 | fast, best quality |
| P1 P2 P3 P4 P5 P6 P7 P8 P9 P10 P11 | SOURCE | 512.6 | source gguf, only provided when it was hard to come by |
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
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.