metadata
language:
- en
library_name: transformers
license: llama2
quantized_by: mradermacher
tags:
- Xwin
- Euryale 1.3
- Platypus2
- WinterGoddess
- frankenmerge
- dare
- ties
- 90b
About
static quants of https://huggingface.co/llmixer/BigWeave-v12-90b
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 | 32.7 | |
| GGUF | IQ3_XS | 36.2 | |
| GGUF | Q3_K_S | 38.2 | |
| GGUF | IQ3_S | 38.4 | fast, beats Q3_K* |
| GGUF | Q3_K_M | 42.6 | lower quality |
| GGUF | Q3_K_L | 46.4 | |
| PART 1 PART 2 | Q4_K_S | 50.2 | fast, medium quality |
| PART 1 PART 2 | Q4_K_M | 53.0 | fast, medium quality |
| PART 1 PART 2 | Q5_K_S | 60.8 | |
| PART 1 PART 2 | Q5_K_M | 62.4 | |
| PART 1 PART 2 | Q6_K | 72.4 | very good quality |
| PART 1 PART 2 | Q8_0 | 93.6 | fast, best quality |
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.