---
base_model: mistralai/Mistral-Nemo-Instruct-2407
library_name: transformers
quantized_by: InferenceIllusionist
language:
- en
- fr
- de
- es
- it
- pt
- ru
- zh
- ja
tags:
- iMat
- gguf
- Mistral
license: apache-2.0
---
# Mistral-Nemo-Instruct-12B-iMat-GGUF
> [!WARNING]
>Important Note: Inferencing is *only* available on this fork of llama.cpp at the moment: https://github.com/iamlemec/llama.cpp/tree/mistral-nemo (All credits to iamlemec for his work on Mistral-Nemo support)
>Other front-ends like the main branch of llama.cpp, kobold.cpp, and text-generation-web-ui may not work as intended
Quantized from Mistral-Nemo-Instruct-2407 fp16
* Weighted quantizations were creating using fp16 GGUF and groups_merged.txt in 92 chunks and n_ctx=512
* Static fp16 will also be included in repo
* For a brief rundown of iMatrix quant performance please see this [PR](https://github.com/ggerganov/llama.cpp/pull/5747)
* All quants are verified working prior to uploading to repo for your safety and convenience
KL-Divergence Reference Chart
(Click on image to view in full size)
[](https://i.imgur.com/mV0nYdA.png)
> [!TIP]
>Quant-specific Tips:
>* If you are getting a `cudaMalloc failed: out of memory` error, try passing an argument for lower context in llama.cpp, e.g. for 8k: `-c 8192`
>* If you have all ampere generation or newer cards, you can use flash attention like so: `-fa`
>* Provided Flash Attention is enabled you can also use quantized cache to save on VRAM e.g. for 8-bit: `-ctk q8_0 -ctv q8_0`
>* Mistral recommends a temperature of 0.3 for this model
Original model card can be found [here](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407)