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

Gemma 4 31B it vs Clover 35B-A3B Preview

Gemma 4 31B it scores 15 on the intelligence index, and Clover 35B-A3B Preview 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, Clover 35B-A3B Preview is about 6.4× quicker: 53 tok/s against 8.3, both estimated from memory bandwidth. At 500k tokens a day the Framework Desktop, 32GB pays for itself in 84 years running Clover 35B-A3B Preview, against 103 years running Gemma 4 31B it.

Gemma 4 31B itClover 35B-A3B Preview
Intelligence index15not placed
ClassHaiku-classnot yet placed
Weights20 GB23 GB
Needs at 32k23 GB24 GB
QuantisationQ4_K_MQ4_K_M
Parameters31.3B34.7B (3B active)
Max context256k128k
API price per 1M$0.1 in / $0.34 out$0.05 in / $0.7 outpriced as Qwen3.6 35B-A3B
LicenceApache 2.0Apache 2.0
Machines here that run it28 of 3728 of 37
Cheapest machine that runs itStrix Halo Framework Desktop, 32GB $1,269Strix Halo Framework Desktop, 32GB $1,269

Run Gemma 4 31B it on the Framework Desktop, 32GB · or Clover 35B-A3B Preview

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 4 31B itClover 35B-A3B Preview
Speed at 32k8.3 tok/s estimated53 tok/s estimated
Pay-back on this machinePays back in 103 yearsPays back in 84 years
API cost per month$1.75$1.38priced as Qwen3.6 35B-A3B

Run Gemma 4 31B it on the Framework Desktop, 32GB · or Clover 35B-A3B Preview

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. Clover 35B-A3B Preview 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 useGemma 4 31B itClover 35B-A3B Preview
50ka few chats a day1,026 years835 years
200klight assistant use257 years209 years
1Ma moderate coding-assistant day51 years42 years
4Mheavy coding with an agent13 years10 years
20Magents running most of the day4.5 yearsits ceiling2.1 years

The Framework Desktop, 32GB generates at most 11.5M tokens a day on Gemma 4 31B it, so that column's figure at 20M tokens a day is for the most it can do, not for the whole of what was asked.

Run Gemma 4 31B it at 20M tokens a day · or Clover 35B-A3B Preview

Memory is not what separates them

Gemma 4 31B it needs 23 GB of memory at 32k of context and Clover 35B-A3B Preview needs 24 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 4 31B it is also head to head with Qwen3.5 122B-A10B above it on the leaderboard, Granite 4.2 30B below it and Gemma 3 27B it, the last-generation Gemma nearest it in size. One more model needs much the same memory: Qwen3.6 35B-A3B.

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 4 31B it · every machine that runs Clover 35B-A3B Preview · every other match-up · both against the frontier · the quickest pay-back at each level of use