TensorBlock

Website Twitter Discord GitHub Telegram

impossibleexchange/o80 - GGUF

This repo contains GGUF format model files for impossibleexchange/o80.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4823.

Our projects

Forge
Forge Project
An OpenAI-compatible multi-provider routing layer.
πŸš€ Try it now! πŸš€
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.
πŸ‘€ See what we built πŸ‘€ πŸ‘€ See what we built πŸ‘€
## Prompt template
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Model file specification

Filename Quant type File Size Description
o80-Q2_K.gguf Q2_K 3.090 GB smallest, significant quality loss - not recommended for most purposes
o80-Q3_K_S.gguf Q3_K_S 3.551 GB very small, high quality loss
o80-Q3_K_M.gguf Q3_K_M 3.880 GB very small, high quality loss
o80-Q3_K_L.gguf Q3_K_L 4.172 GB small, substantial quality loss
o80-Q4_0.gguf Q4_0 4.497 GB legacy; small, very high quality loss - prefer using Q3_K_M
o80-Q4_K_S.gguf Q4_K_S 4.525 GB small, greater quality loss
o80-Q4_K_M.gguf Q4_K_M 4.736 GB medium, balanced quality - recommended
o80-Q5_0.gguf Q5_0 5.388 GB legacy; medium, balanced quality - prefer using Q4_K_M
o80-Q5_K_S.gguf Q5_K_S 5.388 GB large, low quality loss - recommended
o80-Q5_K_M.gguf Q5_K_M 5.511 GB large, very low quality loss - recommended
o80-Q6_K.gguf Q6_K 6.334 GB very large, extremely low quality loss
o80-Q8_0.gguf Q8_0 8.202 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/o80-GGUF --include "o80-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/o80-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
Downloads last month
57
GGUF
Model size
8B params
Architecture
llama
Hardware compatibility
Log In to view the estimation

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for tensorblock/o80-GGUF

Quantized
(1)
this model