---
license: apache-2.0
pipeline_tag: text-generation
library_name: gguf
base_model: Vezora/Mistral-22B-v0.2
---

## About

static quantize of https://huggingface.co/Vezora/Mistral-22B-v0.2
iQ Quants can be found here(Richard Erkhov's work): https://huggingface.co/RichardErkhov/Vezora_-_Mistral-22B-v0.2-gguf

## Provided Quants

| Filename | Quant type | File Size | Description |
| -------- | ---------- | --------- | ----------- |
| [Mistral-22B-v0.2-Q5_K_M.gguf](https://huggingface.co/NLPark/Mistral-22B-v0.2-GGUF/blob/main/Mistral-22B-v0.1-Q5_K_M.gguf) | Q5_K_M | 15.71GB | High quality, *recommended*. |
| [Mistral-22B-v0.2-Q4_K_M.gguf](https://huggingface.co/NLPark/Mistral-22B-v0.2-GGUF/blob/main/Mistral-22B-v0.1-Q4_K_M.gguf) | Q4_K_M | 13.33GB | Good quality, uses about 4.83 bits per weight, *recommended*. |
| [Mistral-22B-v0.2-Q4_K_S.gguf](https://huggingface.co/NLPark/Mistral-22B-v0.2-GGUF/blob/main/Mistral-22B-v0.1-Q4_K_S.gguf) | Q4_K_S | 12.65GB | Slightly lower performance than Q4_K_M, fastest, best choice for 16G RAM devices, *recommended*. |
| [Mistral-22B-v0.2-Q3_K_M.gguf](https://huggingface.co/NLPark/Mistral-22B-v0.2-GGUF/blob/main/Mistral-22B-v0.1-Q3_K_M.gguf) | Q3_K_M | 10.75GB | Even lower quality. |
| [Mistral-22B-v0.2-Q2_K.gguf](https://huggingface.co/NLPark/Mistral-22B-v0.2-GGUF/blob/main/Mistral-22B-v0.1-Q2_K.gguf) | Q2_K | 8.26GB | Very low quality. |