metadata
base_model:
- 152334H/miqu-1-70b-sf
- lizpreciatior/lzlv_70b_fp16_hf
language:
- en
library_name: transformers
quantized_by: mradermacher
tags:
- mergekit
- merge
About
weighted/imatrix quants of https://huggingface.co/wolfram/miquliz-120b-v2.0
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 | 25.6 | |
| GGUF | i1-IQ2_XXS | 32.1 | |
| GGUF | i1-IQ2_XS | 35.7 | |
| GGUF | i1-Q2_K | 44.5 | IQ3_XXS probably better |
| GGUF | i1-IQ3_XXS | 47.2 | fast, lower quality |
| PART 1 PART 2 | i1-Q3_K_XS | 49.2 | |
| PART 1 PART 2 | i1-Q3_K_S | 52.1 | IQ3_XS probably better |
| PART 1 PART 2 | i1-Q3_K_M | 58.1 | IQ3_S probably better |
| PART 1 PART 2 | i1-Q3_K_L | 63.3 | IQ3_M probably better |
| PART 1 PART 2 | i1-Q4_K_S | 68.6 | almost as good as Q4_K_M |
| PART 1 PART 2 | i1-Q4_K_M | 72.5 | fast, medium quality |
| PART 1 PART 2 | i1-Q5_K_M | 85.3 | best weighted quant |
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