gpt-oss-20b vs Gemma 4 E4B
gpt-oss-20b and Gemma 4 E4B both score 9 on the intelligence index. The cheapest machine here that runs gpt-oss-20b is the Mac mini M6, 24GB, at $1,099. Gemma 4 E4B runs on the Mac mini M6, 16GB at $899, $200 less. On the Mac mini M6, 24GB, the cheapest machine here that runs both, gpt-oss-20b is about 1.2× quicker: 18 tok/s against 15, both estimated from memory bandwidth. At 500k tokens a day the Mac mini M6, 24GB pays for itself in 518 years running gpt-oss-20b, against 633 years running Gemma 4 E4B.
| gpt-oss-20b | Gemma 4 E4B | |
|---|---|---|
| Intelligence index | 9 | 9 |
| Class | Below every hosted tier | Below every hosted tier |
| Weights | 12 GB | 5.2 GB |
| Needs at 32k | 13 GB | 5.7 GB |
| Quantisation | MXFP4 | QAT Q4_0 |
| Parameters | 20.9B (3.6B active) | 8B (4.5B active) |
| Max context | 128k | 128k |
| API price per 1M | $0.018 in / $0.09 out | $0.018 in / $0.09 outpriced as gpt-oss-20b |
| Licence | Apache 2.0 | Apache 2.0 |
| Machines here that run it | 33 of 37 | 37 of 37 |
| Cheapest machine that runs it | Mac mini M6, 24GB $1,099 | Mac mini M6, 16GB $899 |
Run gpt-oss-20b on the Mac mini M6, 24GB · or Gemma 4 E4B on the Mac mini M6, 16GB
Jump to: Side by side on the Mac mini M6, 24GB · How much use it takes to pay for the machine · Machines that run one and not the other · The assumptions behind both columns
Side by side on the Mac mini M6, 24GB
The table above gives each model the cheapest machine that runs it, and those are two different machines, so nothing in it is a like-for-like race. The Mac mini M6, 24GB is the cheapest machine here that runs both, so this is the pair doing the same work on the same hardware.
| gpt-oss-20b | Gemma 4 E4B | |
|---|---|---|
| Speed at 32k | 18 tok/s estimated | 15 tok/s estimated |
| Pay-back on this machine | Pays back in 518 years | Pays back in 633 years |
| API cost per month | $0.34 | $0.34priced as gpt-oss-20b |
Run gpt-oss-20b on the Mac mini M6, 24GB · or Gemma 4 E4B
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, 24GB. gpt-oss-20b 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 | gpt-oss-20b | Gemma 4 E4B |
|---|---|---|
| 50ka few chats a day | 5,180 years | 6,331 years |
| 200klight assistant use | 1,295 years | 1,583 years |
| 1Ma moderate coding-assistant day | 259 years | 317 years |
| 4Mheavy coding with an agent | 65 years | 79 years |
| 20Magents running most of the day | 13 years | 16 years |
Run gpt-oss-20b at 20M tokens a day · or Gemma 4 E4B
Machines that run one and not the other
Gemma 4 E4B needs 5.7 GB of memory at 32k of context and gpt-oss-20b needs 13 GB. That puts Gemma 4 E4B on 4 of the 37 machines priced here that gpt-oss-20b does not, starting at $899.
| Machine | Price | Memory | Speed on Gemma 4 E4B | Pay-back |
|---|---|---|---|---|
| Mac mini M6, 16GB | $899 | 16 GB | 13 tok/s estimated | Pays back in 611 years |
| MacBook Air M5 (13-inch), 16GB | $1,299 | 16 GB | 13 tok/s estimated | Pays back in 882 years |
| MacBook Air M5 (15-inch), 16GB | $1,499 | 16 GB | 13 tok/s estimated | Pays back in 1,018 years |
| MacBook Pro M5 (14-inch), 16GB | $1,999 | 16 GB | 13 tok/s estimated | Pays back in 1,358 years |
gpt-oss-20b is also head to head with Qwen3-Coder Next above it on the leaderboard. One more model needs much the same memory: Ministral 3 14B. Gemma 4 E4B is also head to head with Devstral 2 123B below it on the leaderboard.
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 gpt-oss-20b · every machine that runs Gemma 4 E4B · every other match-up · both against the frontier · the quickest pay-back at each level of use