~/model/huggingfacegoogle/gemma-2-9b-it
Google provider

Gemma 2 9B

Google's 2024 9B. Solid baseline; shorter context than Gemma 4.

Parameters
9B
Family
Google
Context
8K tokens
FP16 weights
18GB
// where you can run it
gemma2:9bLM StudiovLLMMLXoMLX
// hugging face stats (cached daily)
410K downloads · 803 likes · license: gemma · updated 1 year ago

What you need to run this.

$ ./vrambudget --model gemma-2-9b --by quant
FP1618 GB
RTX 309024 GB · fitsRTX 3090 Ti24 GB · fitsRTX 409024 GB · fitsRX 7900 XTX24 GB · fits
Q8_09.6 GB
RTX 4060 Ti 16GB16 GB · fitsRTX 4070 Ti Super16 GB · fitsRTX 408016 GB · fitsRTX 4080 Super16 GB · fits
Q6_K7.4 GB
RTX 3060 12GB12 GB · fitsRTX 3080 Ti12 GB · fitsRTX 407012 GB · fitsRTX 4070 Super12 GB · fits
Q5_K_M6.2 GB
RTX 308010 GB · fitsRTX 3060 12GB12 GB · fitsRTX 3080 Ti12 GB · fitsRTX 407012 GB · fits
Q4_K_M5.1 GB
RTX 30708 GB · fitsRTX 40608 GB · fitsRTX 308010 GB · fitsRTX 3060 12GB12 GB · fits

// budgets shown at ctx 8K, concurrency 1, 15% safety headroom. Tune in the calculator →

Alternatives at this size.

$ grep --params similar catalog.json
$ similarQwen 3.5 9B9BAlibaba$ similarLlama 3.1 8B8BMeta$ similarGranite 8B Code8BIBM$ similarMistral 7B v0.37.2BMistral

Discussion.

$ gh discussion list

// sign in with github to leave a comment. threads live in the repo's discussions tab.