Qwen3.5 122B-A10B vs Gemma 4 31B it
Qwen3.5 122B-A10B scores higher on the intelligence index, 16 against 15. The cheapest machine here that runs Qwen3.5 122B-A10B is the Framework Desktop, 128GB, at $3,449. Gemma 4 31B it runs on the Framework Desktop, 32GB at $1,269, $2,180 less. On the Framework Desktop, 128GB, the cheapest machine here that runs both, Qwen3.5 122B-A10B is about 2.4× quicker: 20 tok/s against 8.3, both estimated from memory bandwidth. At 500k tokens a day the Framework Desktop, 128GB pays for itself in 53 years running Qwen3.5 122B-A10B, against 279 years running Gemma 4 31B it.
| Qwen3.5 122B-A10B | Gemma 4 31B it | |
|---|---|---|
| Intelligence index | 16 | 15 |
| Class | Haiku-class | Haiku-class |
| Weights | 78 GB | 20 GB |
| Needs at 32k | 79 GB | 23 GB |
| Quantisation | UD-Q4_K_M | Q4_K_M |
| Parameters | 125.1B (10B active) | 31.3B |
| Max context | 256k | 256k |
| API price per 1M | $0.26 in / $2.08 out | $0.1 in / $0.34 out |
| Licence | Apache 2.0 | Apache 2.0 |
| Machines here that run it | 12 of 37 | 28 of 37 |
| Cheapest machine that runs it | Strix Halo Framework Desktop, 128GB $3,449 | Strix Halo Framework Desktop, 32GB $1,269 |
Run Qwen3.5 122B-A10B on the Framework Desktop, 128GB · or Gemma 4 31B it on the Framework Desktop, 32GB
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.
| Qwen3.5 122B-A10B | Gemma 4 31B it | |
|---|---|---|
| Speed at 32k | 20 tok/s estimated | 8.3 tok/s estimated |
| Pay-back on this machine | Pays back in 53 years | Pays back in 279 years |
| API cost per month | $5.69 | $1.75 |
Run Qwen3.5 122B-A10B on the Framework Desktop, 128GB · or Gemma 4 31B it
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. Qwen3.5 122B-A10B 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 | Qwen3.5 122B-A10B | Gemma 4 31B it |
|---|---|---|
| 50ka few chats a day | 533 years | 2,789 years |
| 200klight assistant use | 133 years | 697 years |
| 1Ma moderate coding-assistant day | 27 years | 139 years |
| 4Mheavy coding with an agent | 6.7 years | 35 years |
| 20Magents running most of the day | 16 months | 12 yearsits ceiling |
The Framework Desktop, 128GB 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 Qwen3.5 122B-A10B at 20M tokens a day · or Gemma 4 31B it
Machines that run one and not the other
Gemma 4 31B it needs 23 GB of memory at 32k of context and Qwen3.5 122B-A10B needs 79 GB. That puts Gemma 4 31B it on 16 of the 37 machines priced here that Qwen3.5 122B-A10B does not, starting at $1,269.
| Machine | Price | Memory | Speed on Gemma 4 31B it | Pay-back |
|---|---|---|---|---|
| Strix Halo Framework Desktop, 32GB | $1,269 | 32 GB | 8.3 tok/s estimated | Pays back in 103 years |
| AMD Radeon AI PRO R9700, 32GB | $1,299card only | 32 GB | 24 tok/s estimated | Pays back in 91 years |
| Strix Halo Corsair AI Workstation 300, 64GB | $1,700 | 64 GB | 8.3 tok/s estimated | Pays back in 137 years |
| Strix Halo Framework Desktop, 64GB | $1,959 | 64 GB | 8.3 tok/s estimated | Pays back in 158 years |
| NVIDIA GeForce RTX 5090, 32GB | $1,999card only | 32 GB | 53 tok/s estimated | Pays back in 131 years |
| Strix Halo GMKtec EVO-X2, 64GB | $2,200 | 64 GB | 8.3 tok/s estimated | Pays back in 195 years |
10 more, on the Gemma 4 31B it page.
Qwen3.5 122B-A10B is also head to head with Gemma 4 26B-A4B above it on the leaderboard. Two more models need much the same memory: Ling 3.0 flash and GLM-4.5-Air. Gemma 4 31B it is also head to head with Granite 4.2 30B below it on the leaderboard 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 Qwen3.5 122B-A10B · every machine that runs Gemma 4 31B it · every other match-up · both against the frontier · the quickest pay-back at each level of use