estimate, except measured file sizes

Can I run Gemma 2 9B locally?

9.24B parameters. Parameter count is an estimate.

Licence:
not recorded
Context:
8,192 tokens
Modality:
not recorded
Released:
not recorded

Gemma 2 alternates local and global attention. The KV cache is an approximation, not a measured file.

· Model page

Memory per quant

KV is at 8,192 tokens. Overhead is 0.8 GB. Both are estimates. A measured file size is labelled. The last column is the cheapest machine that fits the total fully.

Memory per quant for Gemma 2 9B
QuantFile sizeKV at 8K+0.8 overheadTotalCheapest full fit
Q89.9 GB est.2.1 GB est.0.8 GB est.12.8 GB est.GeForce RTX 4060 Ti 16GB, €899 (new (lowest in-stock EU))
Q45.5 GB est.2.1 GB est.0.8 GB est.8.5 GB est.GeForce RTX 3060 12GB, €257 (used (median of sold listings))

Cheapest rig that fits

Q4, full: GeForce RTX 3060 12GB, €257 (used (median of sold listings))

Q4, slow, partly in system RAM: Nothing on our list of 29 machines fits this quant.

On a specific GPU

Can I run Gemma 2 9B locally? VRAM per quant and cheapest rig (EU prices) · localLLMrig