What hardware do you need to run Gemma 3 12B it?
Gemma 3 12B it at Q4_K_M is 7.3 GB of weights, with a context ceiling of 128k tokens. Strong multilingual for its size and light on KV cache. Not a coding model.
How good is it, really?
On the Artificial Analysis Intelligence Index v4.3 it scores 4, which puts it in the Below every hosted tier band. Fine for simple, well-specified tasks. Noticeably less capable than anything the big labs sell today. Score source. See the whole table.
- Summarising — good
- Translation — good
- Everyday coding — usable
- Reasoning & maths — don’t
- Agentic work — don’t
What it costs either way
Renting the same model costs $0.05 per million input tokens and $0.15 per million output (OpenRouter, cheapest active endpoint, checked 2026-09-03). Buying a machine only beats that if you use it hard enough, for long enough, that the hardware price divides down below the rental bill.
Machines that run it
| Machine | Price | Speed at 32k | Pay-back | |
|---|---|---|---|---|
| Mac mini M6, 16GB | $899 | 12 tok/s estimated | Pays back in 123 years | Run the numbers |
| Strix Halo Framework Desktop, 32GB | $1,269 | 20 tok/s estimated | Pays back in 192 years | Run the numbers |
| MacBook Air M5 (13-inch), 16GB | $1,299 | 12 tok/s estimated | Pays back in 178 years | Run the numbers |
| MacBook Pro M5 (14-inch), 16GB | $1,999 | 12 tok/s estimated | Pays back in 274 years | Run the numbers |
| Mac Studio M5 Max, 36GB | $2,499 | 35 tok/s estimated | Pays back in 310 years | Run the numbers |
| DGX Spark GB10 Grace Blackwell, 128GB | $4,699 | 21 tok/s estimated | Pays back in 733 years | Run the numbers |
One machine per family, cheapest first. Speeds are measured where a public benchmark exists and estimated from memory bandwidth otherwise; the calculator says which for any configuration.
The specifics
- Parameters
- 12.2B
- Quantisation
- Q4_K_M
- Weights on disk
- 7.3 GB
- KV cache
- 2.5 GB at 32k context — 5 of every 6 layers use a 1024-token sliding window, so the KV cache barely grows with context.
- Maximum context
- 128k tokens (128k input)
- Licence
- Gemma Terms of Use
- Sources
- source 1, source 2