About
static quants of https://huggingface.co/Vezora/Mistral-22B-v0.2
No imatrix quants will be coming from me, as the model overflowed after 180k tokens and llama.cpp crashed generating most quants with smaller training data.
weighted/imatrix quants by bartowksi (with smaller training data) can be found at https://huggingface.co/bartowski/Mistral-22B-v0.2-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 | 8.4 | |
GGUF | IQ3_XS | 9.3 | |
GGUF | Q3_K_S | 9.7 | |
GGUF | IQ3_S | 9.8 | beats Q3_K* |
GGUF | IQ3_M | 10.2 | |
GGUF | Q3_K_M | 10.9 | lower quality |
GGUF | Q3_K_L | 11.8 | |
GGUF | IQ4_XS | 12.1 | |
GGUF | Q4_K_S | 12.8 | fast, recommended |
GGUF | Q4_K_M | 13.4 | fast, recommended |
GGUF | Q5_K_S | 15.4 | |
GGUF | Q5_K_M | 15.8 | |
GGUF | Q6_K | 18.3 | very good quality |
GGUF | Q8_0 | 23.7 | 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.
- Downloads last month
- 216
Model tree for mradermacher/Mistral-22B-v0.2-GGUF
Base model
Vezora/Mistral-22B-v0.2