Quantization made by Richard Erkhov.

gemma-2-9b - GGUF

Model creator: https://huggingface.co/unsloth/
Original model: https://huggingface.co/unsloth/gemma-2-9b/

Name	Quant method	Size
gemma-2-9b.Q2_K.gguf	Q2_K	3.54GB
gemma-2-9b.IQ3_XS.gguf	IQ3_XS	3.86GB
gemma-2-9b.IQ3_S.gguf	IQ3_S	4.04GB
gemma-2-9b.Q3_K_S.gguf	Q3_K_S	4.04GB
gemma-2-9b.IQ3_M.gguf	IQ3_M	4.19GB
gemma-2-9b.Q3_K.gguf	Q3_K	4.43GB
gemma-2-9b.Q3_K_M.gguf	Q3_K_M	4.43GB
gemma-2-9b.Q3_K_L.gguf	Q3_K_L	4.78GB
gemma-2-9b.IQ4_XS.gguf	IQ4_XS	4.86GB
gemma-2-9b.Q4_0.gguf	Q4_0	5.07GB
gemma-2-9b.IQ4_NL.gguf	IQ4_NL	5.1GB
gemma-2-9b.Q4_K_S.gguf	Q4_K_S	5.1GB
gemma-2-9b.Q4_K.gguf	Q4_K	5.37GB
gemma-2-9b.Q4_K_M.gguf	Q4_K_M	5.37GB
gemma-2-9b.Q4_1.gguf	Q4_1	5.55GB
gemma-2-9b.Q5_0.gguf	Q5_0	6.04GB
gemma-2-9b.Q5_K_S.gguf	Q5_K_S	6.04GB
gemma-2-9b.Q5_K.gguf	Q5_K	6.19GB
gemma-2-9b.Q5_K_M.gguf	Q5_K_M	6.19GB
gemma-2-9b.Q5_1.gguf	Q5_1	6.52GB
gemma-2-9b.Q6_K.gguf	Q6_K	7.07GB
gemma-2-9b.Q8_0.gguf	Q8_0	9.15GB

Original model description:

language: - en library_name: transformers license: gemma tags: - unsloth - transformers - gemma2 - gemma

Reminder to use the dev version Transformers:

pip install git+https://github.com/huggingface/transformers.git

Finetune Gemma, Llama 3, Mistral 2-5x faster with 70% less memory via Unsloth!

Directly quantized 4bit model with bitsandbytes.

We have a Google Colab Tesla T4 notebook for Gemma 2 (9B) here: https://colab.research.google.com/drive/1vIrqH5uYDQwsJ4-OO3DErvuv4pBgVwk4?usp=sharing

✨ Finetune for Free

All notebooks are beginner friendly! Add your dataset, click "Run All", and you'll get a 2x faster finetuned model which can be exported to GGUF, vLLM or uploaded to Hugging Face.

Unsloth supports	Free Notebooks	Performance	Memory use
Llama 3 (8B)	▶️ Start on Colab	2.4x faster	58% less
Gemma 2 (9B)	▶️ Start on Colab	2x faster	63% less
Mistral (9B)	▶️ Start on Colab	2.2x faster	62% less
Phi 3 (mini)	▶️ Start on Colab	2x faster	63% less
TinyLlama	▶️ Start on Colab	3.9x faster	74% less
CodeLlama (34B) A100	▶️ Start on Colab	1.9x faster	27% less
Mistral (7B) 1xT4	▶️ Start on Kaggle	5x faster*	62% less
DPO - Zephyr	▶️ Start on Colab	1.9x faster	19% less

This conversational notebook is useful for ShareGPT ChatML / Vicuna templates.
This text completion notebook is for raw text. This DPO notebook replicates Zephyr.
* Kaggle has 2x T4s, but we use 1. Due to overhead, 1x T4 is 5x faster.