About
static quants of https://huggingface.co./IBI-CAAI/MELT-llama-2-3x70b-chat-hf
weighted/imatrix quants are available at https://huggingface.co./mradermacher/MELT-llama-2-3x70b-chat-hf-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 | 66.4 | |
| PART 1 PART 2 | IQ3_XS | 74.2 | |
| PART 1 PART 2 | IQ3_S | 78.5 | beats Q3_K* |
| PART 1 PART 2 | Q3_K_S | 78.5 | |
| PART 1 PART 2 | IQ3_M | 80.1 | |
| PART 1 PART 2 | Q3_K_M | 87.1 | lower quality |
| PART 1 PART 2 | Q3_K_L | 94.4 | |
| PART 1 PART 2 | IQ4_XS | 97.9 | |
| PART 1 PART 2 PART 3 | Q4_K_S | 103.4 | fast, recommended |
| PART 1 PART 2 PART 3 | Q4_K_M | 109.8 | fast, recommended |
| PART 1 PART 2 PART 3 | Q5_K_S | 125.1 | |
| PART 1 PART 2 PART 3 | Q5_K_M | 128.9 | |
| PART 1 PART 2 PART 3 PART 4 | Q6_K | 149.2 | very good quality |
| PART 1 PART 2 PART 3 PART 4 | Q8_0 | 193.2 | 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.
Model tree for mradermacher/MELT-llama-2-3x70b-chat-hf-GGUF
Base model
IBI-CAAI/MELT-llama-2-3x70b-chat-hf