Qwen3.5 9B vs Nemotron 3.5 Lightning 30B-A3B
Qwen3.5 9B and Nemotron 3.5 Lightning 30B-A3B both score 14 on the intelligence index. The cheapest machine here that runs Nemotron 3.5 Lightning 30B-A3B is the Radeon AI PRO R9700, 32GB, at $1,299. Qwen3.5 9B runs on the Mac mini M6, 16GB at $899, $400 less. The Radeon AI PRO R9700, 32GB is priced as the card alone, without the PC around it. On the Radeon AI PRO R9700, 32GB, the cheapest machine here that runs both, Nemotron 3.5 Lightning 30B-A3B is about 1.5× quicker: 127 tok/s against 82, both estimated from memory bandwidth. At 500k tokens a day the Radeon AI PRO R9700, 32GB pays for itself in 98 years running Qwen3.5 9B, against 297 years running Nemotron 3.5 Lightning 30B-A3B.
| Qwen3.5 9B | Nemotron 3.5 Lightning 30B-A3B | |
|---|---|---|
| Intelligence index | 14 | 14 |
| Class | Below every hosted tier | Below every hosted tier |
| Weights | 5.7 GB | 25 GB |
| Needs at 32k | 6.8 GB | 26 GB |
| Quantisation | Q4_K_M | Q4_K_M |
| Parameters | 9.7B | 31.6B (3B active) |
| Max context | 256k | 256k |
| API price per 1M | $0.08 in / $0.13 out | $0.025 in / $0.12 out |
| Licence | Apache 2.0 | OpenMDW 1.1 |
| Machines here that run it | 37 of 37 | 27 of 37 |
| Cheapest machine that runs it | Mac mini M6, 16GB $899 | AMD Radeon AI PRO R9700, 32GB $1,299card only |
Run Qwen3.5 9B on the Mac mini M6, 16GB · or Nemotron 3.5 Lightning 30B-A3B on the Radeon AI PRO R9700, 32GB
Jump to: Side by side on the Radeon AI PRO R9700, 32GB · 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 Radeon AI PRO R9700, 32GB
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 AMD Radeon AI PRO R9700, 32GB is the cheapest machine here that runs both, so this is the pair doing the same work on the same hardware.
| Qwen3.5 9B | Nemotron 3.5 Lightning 30B-A3B | |
|---|---|---|
| Speed at 32k | 82 tok/s estimated | 127 tok/s estimated |
| Pay-back on this machine | Pays back in 98 years | Pays back in 297 years |
| API cost per month | $1.27 | $0.47 |
Run Qwen3.5 9B on the Radeon AI PRO R9700, 32GB · or Nemotron 3.5 Lightning 30B-A3B
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 Radeon AI PRO R9700, 32GB. Qwen3.5 9B 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 9B | Nemotron 3.5 Lightning 30B-A3B |
|---|---|---|
| 50ka few chats a day | 983 years | 2,968 years |
| 200klight assistant use | 246 years | 742 years |
| 1Ma moderate coding-assistant day | 49 years | 148 years |
| 4Mheavy coding with an agent | 12 years | 37 years |
| 20Magents running most of the day | 2.5 years | 7.4 years |
Run Qwen3.5 9B at 20M tokens a day · or Nemotron 3.5 Lightning 30B-A3B
Machines that run one and not the other
Qwen3.5 9B needs 6.8 GB of memory at 32k of context and Nemotron 3.5 Lightning 30B-A3B needs 26 GB. That puts Qwen3.5 9B on 10 of the 37 machines priced here that Nemotron 3.5 Lightning 30B-A3B does not, starting at $899.
| Machine | Price | Memory | Speed on Qwen3.5 9B | Pay-back |
|---|---|---|---|---|
| Mac mini M6, 16GB | $899 | 16 GB | 17 tok/s estimated | Pays back in 69 years |
| Mac mini M6, 24GB | $1,099 | 24 GB | 19 tok/s estimated | Pays back in 82 years |
| Strix Halo Framework Desktop, 32GB | $1,269 | 32 GB | 28 tok/s estimated | Pays back in 100 years |
| Mac mini M6, 32GB | $1,299 | 32 GB | 19 tok/s estimated | Pays back in 97 years |
| MacBook Air M5 (13-inch), 16GB | $1,299 | 16 GB | 17 tok/s estimated | Pays back in 99 years |
| MacBook Air M5 (15-inch), 16GB | $1,499 | 16 GB | 17 tok/s estimated | Pays back in 114 years |
4 more, on the Qwen3.5 9B page.
Qwen3.5 9B is also head to head with Gemma 4 12B above it on the leaderboard and Qwen3 8B, the last-generation Qwen nearest it in size. Nemotron 3.5 Lightning 30B-A3B is also head to head with Qwen3 235B-A22B Instruct 2507 below it on the leaderboard. One more model needs much the same memory: Granite 4.2 30B.
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 9B · every machine that runs Nemotron 3.5 Lightning 30B-A3B · every other match-up · both against the frontier · the quickest pay-back at each level of use