---
base_model: niallturbitt/mpt-3b-8k-instruct
inference: false
model_creator: niallturbitt
model_name: mpt-3b-8k-instruct
pipeline_tag: text-generation
quantized_by: afrideva
tags:
- gguf
- ggml
- quantized
- q2_k
- q3_k_m
- q4_k_m
- q5_k_m
- q6_k
- q8_0
---
# niallturbitt/mpt-3b-8k-instruct-GGUF

Quantized GGUF model files for [mpt-3b-8k-instruct](https://huggingface.co/niallturbitt/mpt-3b-8k-instruct) from [niallturbitt](https://huggingface.co/niallturbitt)


| Name | Quant method | Size |
| ---- | ---- | ---- |
| [mpt-3b-8k-instruct.q2_k.gguf](https://huggingface.co/afrideva/mpt-3b-8k-instruct-GGUF/resolve/main/mpt-3b-8k-instruct.q2_k.gguf) | q2_k | 1.54 GB  |
| [mpt-3b-8k-instruct.q3_k_m.gguf](https://huggingface.co/afrideva/mpt-3b-8k-instruct-GGUF/resolve/main/mpt-3b-8k-instruct.q3_k_m.gguf) | q3_k_m | 1.95 GB  |
| [mpt-3b-8k-instruct.q4_k_m.gguf](https://huggingface.co/afrideva/mpt-3b-8k-instruct-GGUF/resolve/main/mpt-3b-8k-instruct.q4_k_m.gguf) | q4_k_m | 2.34 GB  |
| [mpt-3b-8k-instruct.q5_k_m.gguf](https://huggingface.co/afrideva/mpt-3b-8k-instruct-GGUF/resolve/main/mpt-3b-8k-instruct.q5_k_m.gguf) | q5_k_m | 2.71 GB  |
| [mpt-3b-8k-instruct.q6_k.gguf](https://huggingface.co/afrideva/mpt-3b-8k-instruct-GGUF/resolve/main/mpt-3b-8k-instruct.q6_k.gguf) | q6_k | 2.98 GB  |
| [mpt-3b-8k-instruct.q8_0.gguf](https://huggingface.co/afrideva/mpt-3b-8k-instruct-GGUF/resolve/main/mpt-3b-8k-instruct.q8_0.gguf) | q8_0 | 3.86 GB  |



## Original Model Card: