metadata
inference: false
library_name: transformers
language:
- en
- fr
- de
- es
- it
- pt
- ja
- ko
- zh
- ar
- el
- fa
- pl
- id
- cs
- he
- hi
- nl
- ro
- ru
- tr
- uk
- vi
license: cc-by-nc-4.0
tags:
- TensorBlock
- GGUF
base_model: adamo1139/aya-expanse-32b-ungated
adamo1139/aya-expanse-32b-ungated - GGUF
This repo contains GGUF format model files for adamo1139/aya-expanse-32b-ungated.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.
Our projects
| Forge | |
|---|---|
|
|
| An OpenAI-compatible multi-provider routing layer. | |
| 🚀 Try it now! 🚀 | |
| Awesome MCP Servers | TensorBlock Studio |
 |
 |
| A comprehensive collection of Model Context Protocol (MCP) servers. | A lightweight, open, and extensible multi-LLM interaction studio. |
| 👀 See what we built 👀 | 👀 See what we built 👀 |
<BOS_TOKEN><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>{system_prompt}<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|USER_TOKEN|>{prompt}<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| aya-expanse-32b-ungated-Q2_K.gguf | Q2_K | 12.811 GB | smallest, significant quality loss - not recommended for most purposes |
| aya-expanse-32b-ungated-Q3_K_S.gguf | Q3_K_S | 14.709 GB | very small, high quality loss |
| aya-expanse-32b-ungated-Q3_K_M.gguf | Q3_K_M | 16.232 GB | very small, high quality loss |
| aya-expanse-32b-ungated-Q3_K_L.gguf | Q3_K_L | 17.563 GB | small, substantial quality loss |
| aya-expanse-32b-ungated-Q4_0.gguf | Q4_0 | 18.719 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| aya-expanse-32b-ungated-Q4_K_S.gguf | Q4_K_S | 18.850 GB | small, greater quality loss |
| aya-expanse-32b-ungated-Q4_K_M.gguf | Q4_K_M | 19.801 GB | medium, balanced quality - recommended |
| aya-expanse-32b-ungated-Q5_0.gguf | Q5_0 | 22.494 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| aya-expanse-32b-ungated-Q5_K_S.gguf | Q5_K_S | 22.494 GB | large, low quality loss - recommended |
| aya-expanse-32b-ungated-Q5_K_M.gguf | Q5_K_M | 23.051 GB | large, very low quality loss - recommended |
| aya-expanse-32b-ungated-Q6_K.gguf | Q6_K | 26.505 GB | very large, extremely low quality loss |
| aya-expanse-32b-ungated-Q8_0.gguf | Q8_0 | 34.327 GB | very large, extremely low quality loss - not recommended |
Downloading instruction
Command line
Firstly, install Huggingface Client
pip install -U "huggingface_hub[cli]"
Then, downoad the individual model file the a local directory
huggingface-cli download tensorblock/aya-expanse-32b-ungated-GGUF --include "aya-expanse-32b-ungated-Q2_K.gguf" --local-dir MY_LOCAL_DIR
If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:
huggingface-cli download tensorblock/aya-expanse-32b-ungated-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'