base_model: microsoft/Phi-3.5-MoE-instruct
language:
- multilingual
library_name: transformers
license: mit
license_link: https://huggingface.co./microsoft/Phi-3.5-MoE-instruct/resolve/main/LICENSE
no_imatrix: 'quantize: line 230: 3149156 Segmentation fault'
quantized_by: mradermacher
tags:
- nlp
- code
About
static quants of https://huggingface.co./microsoft/Phi-3.5-MoE-instruct
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 | 15.4 | |
| GGUF | Q3_K_S | 18.2 | |
| GGUF | Q3_K_M | 20.1 | lower quality |
| GGUF | Q3_K_L | 21.8 | |
| GGUF | IQ4_XS | 22.7 | |
| GGUF | Q4_K_S | 23.9 | fast, recommended |
| GGUF | Q4_K_M | 25.4 | fast, recommended |
| GGUF | Q5_K_S | 28.9 | |
| GGUF | Q5_K_M | 29.8 | |
| GGUF | Q6_K | 34.5 | very good quality |
| GGUF | Q8_0 | 44.6 | 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
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.