Sunk Cost sunkcost.ai Data checked 2026-09-03

Ministral 3 8B vs Ternary Bonsai 2 27B

Ministral 3 8B scores 5 on the intelligence index, and Ternary Bonsai 2 27B has not been placed on it. Both take the same machine to start: the cheapest here that runs either is the Mac mini M6, 16GB, at $899. On it, they run at much the same speed: 12 and 12 tok/s, both estimated from memory bandwidth. At 500k tokens a day the Mac mini M6, 16GB pays for itself in 37 years running Ministral 3 8B, against 58 years running Ternary Bonsai 2 27B.

Ministral 3 8BTernary Bonsai 2 27B
Intelligence index5not placed
ClassBelow every hosted tiernot yet placed
Weights5.2 GB7.6 GB
Needs at 32k9.8 GB9.8 GB
QuantisationQ4_K_MQ2_0
Parameters8.9B27.8B
Max context256k256k
API price per 1M$0.15 in / $0.15 out$0.075 in / $0.5 out
LicenceApache 2.0Apache 2.0
Machines here that run it37 of 3737 of 37
Cheapest machine that runs itMac mini M6, 16GB $899Mac mini M6, 16GB $899

Run Ministral 3 8B on the Mac mini M6, 16GB · or Ternary Bonsai 2 27B

Jump to: Side by side on the Mac mini M6, 16GB · 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 Mac mini M6, 16GB

The cheapest machine that runs either model is the same one, so this is the pair doing the same work on the same hardware: Mac mini M6, 16GB, at $899.

Ministral 3 8BTernary Bonsai 2 27B
Speed at 32k12 tok/s estimated12 tok/s estimated
Pay-back on this machinePays back in 37 yearsPays back in 58 years
API cost per month$2.28$1.55

Run Ministral 3 8B on the Mac mini M6, 16GB · or Ternary Bonsai 2 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 Mac mini M6, 16GB. Ministral 3 8B 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 useMinistral 3 8BTernary Bonsai 2 27B
50ka few chats a day368 years578 years
200klight assistant use92 years144 years
1Ma moderate coding-assistant day18 years29 years
4Mheavy coding with an agent4.6 years7.2 years
20Magents running most of the day14 monthsits ceiling21 monthsits ceiling

The Mac mini M6, 16GB cannot generate 20M tokens a day on either model: at most 16.2M on Ministral 3 8B and 16.2M on Ternary Bonsai 2 27B. Both figures on that row are for the most it can do.

Run Ministral 3 8B at 20M tokens a day · or Ternary Bonsai 2 27B

Memory is not what separates them

Both need 9.8 GB of memory at 32k of context. 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 and what the same work costs on an API, not what you have to buy to hold it.

Ministral 3 8B is also head to head with Gemma 3 27B it above it on the leaderboard and Gemma 3 12B it below it. One more model needs much the same memory: Llama 3.1 8B Instruct. Ternary Bonsai 2 27B is also head to head with Gemma 3 12B it, which needs 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 Ministral 3 8B · every machine that runs Ternary Bonsai 2 27B · every other match-up · both against the frontier · the quickest pay-back at each level of use