metadata
language:
- en
library_name: transformers
license: llama2
quantized_by: mradermacher
About
static quantize of https://huggingface.co/sophosympatheia/Midnight-Rose-103B-v2.0.3/
weighted/imatrix wuants can be found at https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-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 | 38.2 | |
| GGUF | Q3_K_XS | 42.3 | |
| GGUF | Q3_K_S | 44.8 | |
| PART 1 PART 2 | Q3_K_M | 49.9 | lower quality |
| PART 1 PART 2 | Q3_K_L | 54.4 | |
| PART 1 PART 2 | Q4_K_S | 58.9 | fast, medium quality |
| PART 1 PART 2 | Q4_K_M | 62.2 | fast, medium quality |
| PART 1 PART 2 | Q5_K_S | 71.3 | |
| PART 1 PART 2 | Q5_K_M | 73.2 | |
| PART 1 PART 2 | Q6_K | 85.0 | very good quality |
| PART 1 PART 2 PART 3 | Q8_0 | 109.9 | fast, best quality |
Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):
