About
static quants of https://huggingface.co/hungchiayu/NORA
For a convenient overview and download list, visit our model page for this model.
weighted/imatrix quants are available at https://huggingface.co/mradermacher/NORA-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 |
|---|---|---|---|
| PART 1 PART 2 | Q2_K | 2.7 | |
| PART 1 PART 2 | mmproj-fp16 | 2.8 | multi-modal supplement |
| PART 1 PART 2 | Q3_K_S | 3.0 | |
| PART 1 PART 2 | Q3_K_M | 3.3 | lower quality |
| PART 1 PART 2 | Q3_K_L | 3.5 | |
| PART 1 PART 2 | IQ4_XS | 3.6 | |
| PART 1 PART 2 | Q4_K_S | 3.8 | fast, recommended |
| PART 1 PART 2 | Q4_K_M | 4.0 | fast, recommended |
| PART 1 PART 2 | Q5_K_S | 4.4 | |
| PART 1 PART 2 | Q5_K_M | 4.6 | |
| PART 1 PART 2 | Q6_K | 5.2 | very good quality |
| PART 1 PART 2 | Q8_0 | 6.7 | fast, best quality |
| PART 1 PART 2 | f16 | 12.5 | 16 bpw, overkill |
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.
- Downloads last month
- 136
2-bit
3-bit
4-bit
5-bit
6-bit
8-bit
16-bit
Model tree for mradermacher/NORA-GGUF
Base model
hungchiayu/NORA