estimate, except measured file sizes

Can I run Gemma 2 27B locally?

27.2B parameters. Parameter count is an estimate.

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

Same caveat as Gemma 2 9B: sliding window makes the KV estimate rougher.

· 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 27B
QuantFile sizeKV at 8K+0.8 overheadTotalCheapest full fit
Q829.1 GB est.2.3 GB est.0.8 GB est.32.2 GB est.Mac mini M4 Pro 64GB, €1,890 (estimate)
Q416.3 GB est.2.3 GB est.0.8 GB est.19.4 GB est.GeForce RTX 3090 24GB, €1,224 (used (median of sold listings))

Cheapest rig that fits

Q4, full: GeForce RTX 3090 24GB, €1,224 (used (median of sold listings))

Q4, slow, partly in system RAM: Budget PC with RTX 3060 12GB, slow, partly in system RAM, €1,357 (estimate)

On a specific GPU

Can I run Gemma 2 27B locally? VRAM per quant and cheapest rig (EU prices) · localLLMrig