---
base_model: euclaise/Ferret-3B
datasets:
- euclaise/MiniCoT
- euclaise/SciCoT
- euclaise/symtune_mini
- euclaise/mathoverflow-accepted
- euirim/goodwiki
inference: false
model_creator: euclaise
model_name: Ferret-3B
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
---
# euclaise/Ferret-3B-GGUF

Quantized GGUF model files for [Ferret-3B](https://huggingface.co/euclaise/Ferret-3B) from [euclaise](https://huggingface.co/euclaise)


| Name | Quant method | Size |
| ---- | ---- | ---- |
| [ferret-3b.fp16.gguf](https://huggingface.co/afrideva/Ferret-3B-GGUF/resolve/main/ferret-3b.fp16.gguf) | fp16 | 5.59 GB  |
| [ferret-3b.q2_k.gguf](https://huggingface.co/afrideva/Ferret-3B-GGUF/resolve/main/ferret-3b.q2_k.gguf) | q2_k | 1.20 GB  |
| [ferret-3b.q3_k_m.gguf](https://huggingface.co/afrideva/Ferret-3B-GGUF/resolve/main/ferret-3b.q3_k_m.gguf) | q3_k_m | 1.39 GB  |
| [ferret-3b.q4_k_m.gguf](https://huggingface.co/afrideva/Ferret-3B-GGUF/resolve/main/ferret-3b.q4_k_m.gguf) | q4_k_m | 1.71 GB  |
| [ferret-3b.q5_k_m.gguf](https://huggingface.co/afrideva/Ferret-3B-GGUF/resolve/main/ferret-3b.q5_k_m.gguf) | q5_k_m | 1.99 GB  |
| [ferret-3b.q6_k.gguf](https://huggingface.co/afrideva/Ferret-3B-GGUF/resolve/main/ferret-3b.q6_k.gguf) | q6_k | 2.30 GB  |
| [ferret-3b.q8_0.gguf](https://huggingface.co/afrideva/Ferret-3B-GGUF/resolve/main/ferret-3b.q8_0.gguf) | q8_0 | 2.97 GB  |



## Original Model Card: