Gemma 3 27B it vs Arete-27B
Gemma 3 27B it scores 5 on the intelligence index, and Arete-27B has not been placed on it. Both take the same machine to start: the cheapest here that runs either is the Framework Desktop, 32GB, at $1,269. On it, they run at much the same speed: 9.8 and 9.9 tok/s, both estimated from memory bandwidth. At 500k tokens a day the Framework Desktop, 32GB pays for itself in 92 years running Arete-27B, against 155 years running Gemma 3 27B it.
| Gemma 3 27B it | Arete-27B | |
|---|---|---|
| Intelligence index | 5 | not placed |
| Class | Below every hosted tier | not yet placed |
| Weights | 17 GB | 17 GB |
| Needs at 32k | 20 GB | 19 GB |
| Quantisation | Q4_K_M | Q4_K_M |
| Parameters | 27.4B | 27.4B |
| Max context | 128k | 256k |
| API price per 1M | $0.08 in / $0.16 out | $0.039 in / $1.25 outpriced as Qwen3.8 27B |
| Licence | Gemma Terms of Use | Apache 2.0 |
| Machines here that run it | 30 of 37 | 30 of 37 |
| Cheapest machine that runs it | Strix Halo Framework Desktop, 32GB $1,269 | Strix Halo Framework Desktop, 32GB $1,269 |
Run Gemma 3 27B it on the Framework Desktop, 32GB · or Arete-27B
Jump to: Side by side on the Framework Desktop, 32GB · How much use it takes to pay for the machine · Memory is not what separates them · The assumptions behind both columns
Side by side on the Framework Desktop, 32GB
The cheapest machine that runs either model is the same one, so this is the pair doing the same work on the same hardware: Strix Halo Framework Desktop, 32GB, at $1,269.
| Gemma 3 27B it | Arete-27B | |
|---|---|---|
| Speed at 32k | 9.8 tok/s estimated | 9.9 tok/s estimated |
| Pay-back on this machine | Pays back in 155 years | Pays back in 92 years |
| API cost per month | $1.29 | $1.75priced as Qwen3.8 27B |
Run Gemma 3 27B it on the Framework Desktop, 32GB · or Arete-27B
How much use it takes to pay for the machine
Everything above is at 500k tokens a day. Pay-back moves with how much you actually run, so here are both models at the five levels of use the calculator names, on the Framework Desktop, 32GB. Arete-27B pays for it sooner at every level of use, so which of them to run does not turn on how hard you work it.
| A day's use | Gemma 3 27B it | Arete-27B |
|---|---|---|
| 50ka few chats a day | 1,552 years | 925 years |
| 200klight assistant use | 388 years | 231 years |
| 1Ma moderate coding-assistant day | 78 years | 46 years |
| 4Mheavy coding with an agent | 19 years | 12 years |
| 20Magents running most of the day | 5.7 yearsits ceiling | 3.4 yearsits ceiling |
The Framework Desktop, 32GB cannot generate 20M tokens a day on either model: at most 13.5M on Gemma 3 27B it and 13.7M on Arete-27B. Both figures on that row are for the most it can do.
Run Gemma 3 27B it at 20M tokens a day · or Arete-27B
Memory is not what separates them
Gemma 3 27B it needs 20 GB of memory at 32k of context and Arete-27B needs 19 GB. Every machine priced here that runs one runs the other, at 32k of context. So the choice between them is what each is good at, how fast it runs and what the same work costs on an API, not what you have to buy to hold it.
Gemma 3 27B it is also head to head with Qwen3 8B above it on the leaderboard, Ministral 3 8B below it and Gemma 4 31B it, the current Gemma nearest it in size. Two more models need much the same memory: Devstral Small 2 24B and Mistral Small 3.2 24B Instruct. Arete-27B is also head to head with Qwen3.8 27B and Qwen3.6 27B, which need much the same memory.
The assumptions behind both columns
Both columns use the same usage: 500k tokens a day at 15:1 input to output, 32k of context, $0.17 per kWh, and today's API prices held flat. Speeds marked estimated are worked out from memory bandwidth rather than measured, and pay-back scales with them. Where nobody rents an open model by the token, its API prices are the nearest hosted model's, named beside them. Machines are the 37 here with a published price that are still sold. Change any of it in the calculator.
More head to head: every machine that runs Gemma 3 27B it · every machine that runs Arete-27B · every other match-up · both against the frontier · the quickest pay-back at each level of use