README.md

metadata

language:
  - en
tags:
  - falcon3
  - falcon3_mamba
  - falcon_mamba
  - TensorBlock
  - GGUF
base_model: tiiuae/Falcon3-Mamba-7B-Instruct
license: other
license_name: falcon-llm-license
license_link: https://falconllm.tii.ae/falcon-terms-and-conditions.html
library_name: transformers

tiiuae/Falcon3-Mamba-7B-Instruct - GGUF

This repo contains GGUF format model files for tiiuae/Falcon3-Mamba-7B-Instruct.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4242.

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 👀

## Prompt template

<|begin_of_text|><|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
Falcon3-Mamba-7B-Instruct-Q2_K.gguf	Q2_K	2.565 GB	smallest, significant quality loss - not recommended for most purposes
Falcon3-Mamba-7B-Instruct-Q3_K_S.gguf	Q3_K_S	3.275 GB	very small, high quality loss
Falcon3-Mamba-7B-Instruct-Q3_K_M.gguf	Q3_K_M	3.275 GB	very small, high quality loss
Falcon3-Mamba-7B-Instruct-Q3_K_L.gguf	Q3_K_L	3.275 GB	small, substantial quality loss
Falcon3-Mamba-7B-Instruct-Q4_0.gguf	Q4_0	4.204 GB	legacy; small, very high quality loss - prefer using Q3_K_M
Falcon3-Mamba-7B-Instruct-Q4_K_S.gguf	Q4_K_S	4.204 GB	small, greater quality loss
Falcon3-Mamba-7B-Instruct-Q4_K_M.gguf	Q4_K_M	4.204 GB	medium, balanced quality - recommended
Falcon3-Mamba-7B-Instruct-Q5_0.gguf	Q5_0	5.078 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Falcon3-Mamba-7B-Instruct-Q5_K_S.gguf	Q5_K_S	5.078 GB	large, low quality loss - recommended
Falcon3-Mamba-7B-Instruct-Q5_K_M.gguf	Q5_K_M	5.078 GB	large, very low quality loss - recommended
Falcon3-Mamba-7B-Instruct-Q6_K.gguf	Q6_K	6.007 GB	very large, extremely low quality loss
Falcon3-Mamba-7B-Instruct-Q8_0.gguf	Q8_0	7.766 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/Falcon3-Mamba-7B-Instruct-GGUF --include "Falcon3-Mamba-7B-Instruct-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/Falcon3-Mamba-7B-Instruct-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'