gpt-oss-120b vs Ling 3.0 tiny
gpt-oss-120b and Ling 3.0 tiny both score 12 on the intelligence index. The cheapest machine here that runs gpt-oss-120b is the Framework Desktop, 128GB, at $3,449. Ling 3.0 tiny runs on the Mac mini M6, 16GB at $899, $2,550 less. On the Framework Desktop, 128GB, the cheapest machine here that runs both, Ling 3.0 tiny is about 3.9× quicker: 138 tok/s against 35, gpt-oss-120b's measured and the other estimated from memory bandwidth. At 500k tokens a day the Framework Desktop, 128GB pays for itself in 301 years running Ling 3.0 tiny, against 720 years running gpt-oss-120b.
| gpt-oss-120b | Ling 3.0 tiny | |
|---|---|---|
| Intelligence index | 12 | 12 |
| Class | Below every hosted tier | Below every hosted tier |
| Weights | 63 GB | 4.8 GB |
| Needs at 32k | 65 GB | 5.0 GB |
| Quantisation | MXFP4 | Q4_K_M |
| Parameters | 116.8B (5.1B active) | 7.9B (1.3B active) |
| Max context | 128k | 128k |
| API price per 1M | $0.03 in / $0.15 out | $0.06 in / $0.15 outpriced as Granite 4.2 8B |
| Licence | Apache 2.0 | MIT |
| Machines here that run it | 13 of 37 | 37 of 37 |
| Cheapest machine that runs it | Strix Halo Framework Desktop, 128GB $3,449 | Mac mini M6, 16GB $899 |
Run gpt-oss-120b on the Framework Desktop, 128GB · or Ling 3.0 tiny on the Mac mini M6, 16GB
Jump to: Side by side on the Framework Desktop, 128GB · 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 Framework Desktop, 128GB
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 Strix Halo Framework Desktop, 128GB is the cheapest machine here that runs both, so this is the pair doing the same work on the same hardware.
| gpt-oss-120b | Ling 3.0 tiny | |
|---|---|---|
| Speed at 32k | 35 tok/s measured | 138 tok/s estimated |
| Pay-back on this machine | Pays back in 720 years | Pays back in 301 years |
| API cost per month | $0.57 | $1.00priced as Granite 4.2 8B |
Run gpt-oss-120b on the Framework Desktop, 128GB · or Ling 3.0 tiny
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, 128GB. Ling 3.0 tiny 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-120b | Ling 3.0 tiny |
|---|---|---|
| 50ka few chats a day | 7,203 years | 3,008 years |
| 200klight assistant use | 1,801 years | 752 years |
| 1Ma moderate coding-assistant day | 360 years | 150 years |
| 4Mheavy coding with an agent | 90 years | 38 years |
| 20Magents running most of the day | 18 years | 7.5 years |
Run gpt-oss-120b at 20M tokens a day · or Ling 3.0 tiny
Machines that run one and not the other
Ling 3.0 tiny needs 5.0 GB of memory at 32k of context and gpt-oss-120b needs 65 GB. That puts Ling 3.0 tiny on 24 of the 37 machines priced here that gpt-oss-120b does not, starting at $899.
| Machine | Price | Memory | Speed on Ling 3.0 tiny | Pay-back |
|---|---|---|---|---|
| Mac mini M6, 16GB | $899 | 16 GB | 45 tok/s estimated | Pays back in 80 years |
| Mac mini M6, 24GB | $1,099 | 24 GB | 50 tok/s estimated | Pays back in 97 years |
| Strix Halo Framework Desktop, 32GB | $1,269 | 32 GB | 138 tok/s estimated | Pays back in 111 years |
| Mac mini M6, 32GB | $1,299 | 32 GB | 50 tok/s estimated | Pays back in 115 years |
| MacBook Air M5 (13-inch), 16GB | $1,299 | 16 GB | 45 tok/s estimated | Pays back in 116 years |
| AMD Radeon AI PRO R9700, 32GB | $1,299card only | 32 GB | 326 tok/s estimated | Pays back in 113 years |
18 more, on the Ling 3.0 tiny page.
gpt-oss-120b is also head to head with Qwen3.5 4B above it on the leaderboard. One more model needs much the same memory: Llama 4 Scout 17B-16E. Ling 3.0 tiny is also head to head with Granite 4.2 8B 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-120b · every machine that runs Ling 3.0 tiny · every other match-up · both against the frontier · the quickest pay-back at each level of use