About
weighted/imatrix quants of https://huggingface.co/nisten/shqiponja-90
static quants are available at https://huggingface.co/mradermacher/shqiponja-90-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 | i1-IQ1_S | 21.7 | for the desperate |
| GGUF | i1-IQ1_M | 23.4 | mostly desperate |
| GGUF | i1-IQ2_XXS | 26.2 | |
| GGUF | i1-IQ2_XS | 28.6 | |
| GGUF | i1-IQ2_S | 30.6 | |
| GGUF | i1-IQ2_M | 32.8 | |
| GGUF | i1-Q2_K | 35.1 | IQ3_XXS probably better |
| GGUF | i1-IQ3_XXS | 36.0 | lower quality |
| GGUF | i1-IQ3_XS | 38.6 | |
| GGUF | i1-IQ3_S | 40.6 | beats Q3_K* |
| GGUF | i1-Q3_K_S | 40.6 | IQ3_XS probably better |
| GGUF | i1-IQ3_M | 42.7 | |
| GGUF | i1-Q3_K_M | 45.3 | IQ3_S probably better |
| GGUF | i1-Q3_K_L | 49.3 | IQ3_M probably better |
| PART 1 PART 2 | i1-IQ4_XS | 49.6 | |
| PART 1 PART 2 | i1-Q4_0 | 52.5 | fast, low quality |
| PART 1 PART 2 | i1-Q4_K_S | 52.7 | optimal size/speed/quality |
| PART 1 PART 2 | i1-Q4_K_M | 55.8 | fast, recommended |
| PART 1 PART 2 | i1-Q5_K_S | 63.4 | |
| PART 1 PART 2 | i1-Q5_K_M | 65.2 | |
| PART 1 PART 2 | i1-Q6_K | 75.2 | 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.
- Downloads last month
- 80