You can deploy this model and start earning money today!

tensorblock/
aya-expanse-32b-GGUF

Name: aya-expanse-32b-GGUF
Availability: InStock

CohereLabs/aya-expanse-32b

Views

No views yet

Website

Discord

GitHub

CohereForAI/aya-expanse-32b - GGUF

This repo contains GGUF format model files for CohereForAI/aya-expanse-32b.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.

Our projects

Forge
Forge Project
An OpenAI-compatible multi-provider routing layer.
🚀 Try it now! 🚀
Awesome MCP Servers	TensorBlock Studio
MCP Servers	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 👀

## Prompt template

<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-Q2_K.gguf	Q2_K	12.811 GB	smallest, significant quality loss - not recommended for most purposes
aya-expanse-32b-Q3_K_S.gguf	Q3_K_S	14.709 GB	very small, high quality loss
aya-expanse-32b-Q3_K_M.gguf	Q3_K_M	16.232 GB	very small, high quality loss
aya-expanse-32b-Q3_K_L.gguf	Q3_K_L	17.563 GB	small, substantial quality loss
aya-expanse-32b-Q4_0.gguf	Q4_0	18.719 GB	legacy; small, very high quality loss - prefer using Q3_K_M
aya-expanse-32b-Q4_K_S.gguf	Q4_K_S	18.850 GB	small, greater quality loss
aya-expanse-32b-Q4_K_M.gguf	Q4_K_M	19.801 GB	medium, balanced quality - recommended
aya-expanse-32b-Q5_0.gguf	Q5_0	22.494 GB	legacy; medium, balanced quality - prefer using Q4_K_M
aya-expanse-32b-Q5_K_S.gguf	Q5_K_S	22.494 GB	large, low quality loss - recommended
aya-expanse-32b-Q5_K_M.gguf	Q5_K_M	23.051 GB	large, very low quality loss - recommended
aya-expanse-32b-Q6_K.gguf	Q6_K	26.505 GB	very large, extremely low quality loss
aya-expanse-32b-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-GGUF --include "aya-expanse-32b-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-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'