About
weighted/imatrix quants of https://huggingface.co/lodrick-the-lafted/Grafted-Titanic-Dolphin-2x120B
No IQ-quants are available because llama.cpp is a crashfest atm. and crashes when trying to generate them.
static quants are available at https://huggingface.co/mradermacher/Grafted-Titanic-Dolphin-2x120B-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 | i1-Q2_K | 78.6 | IQ3_XXS probably better |
| PART 1 PART 2 | i1-Q3_K_S | 92.6 | IQ3_XS probably better |
| PART 1 PART 2 PART 3 | i1-Q3_K_M | 103.0 | IQ3_S probably better |
| PART 1 PART 2 PART 3 | i1-Q3_K_L | 111.9 | IQ3_M probably better |
| PART 1 PART 2 PART 3 | i1-Q4_K_S | 122.0 | optimal size/speed/quality |
| PART 1 PART 2 PART 3 | i1-Q4_K_M | 129.5 | fast, recommended |
| PART 1 PART 2 PART 3 PART 4 | i1-Q5_K_S | 147.8 | |
| PART 1 PART 2 PART 3 PART 4 | i1-Q5_K_M | 152.2 | |
| PART 1 PART 2 PART 3 PART 4 | i1-Q6_K | 176.2 | practically like static Q6_K |
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.