metadata
base_model:
- 152334H/miqu-1-70b-sf
language:
- en
library_name: transformers
quantized_by: mradermacher
tags:
- mergekit
- merge
About
static quants of https://huggingface.co/wolfram/miqu-1-103b
weighted/imatrix quants are available at https://huggingface.co/mradermacher/miqu-1-103b-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 | 38.3 | |
| GGUF | IQ3_XS | 42.5 | |
| GGUF | Q3_K_S | 44.9 | |
| GGUF | IQ3_S | 45.0 | fast, beats Q3_K* |
| GGUF | IQ3_M | 46.5 | |
| PART 1 PART 2 | Q3_K_M | 50.0 | lower quality |
| PART 1 PART 2 | Q3_K_L | 54.5 | |
| PART 1 PART 2 | IQ4_XS | 56.0 | |
| PART 1 PART 2 | Q4_K_S | 59.0 | fast, medium quality |
| PART 1 PART 2 | IQ4_NL | 59.1 | fast, slightly worse than Q4_K_S |
| PART 1 PART 2 | Q4_K_M | 62.3 | fast, medium quality |
| PART 1 PART 2 | Q5_K_S | 71.4 | |
| PART 1 PART 2 | Q5_K_M | 73.3 | |
| PART 1 PART 2 | Q6_K | 85.1 | very good quality |
| PART 1 PART 2 PART 3 | Q8_0 | 110.0 | 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