Nemotron 3.5 Bolt 74B-A9B vs Qwen3 30B-A3B Instruct 2507
Nemotron 3.5 Bolt 74B-A9B scores higher on the intelligence index, 21 against 10. Both take the same machine to start: the cheapest here that runs either is the Framework Desktop, 32GB, at $1,269. On it, Nemotron 3.5 Bolt 74B-A9B is about 1.8× quicker: 48 tok/s against 27, both estimated from memory bandwidth. At 500k tokens a day the Framework Desktop, 32GB pays for itself in 17 years running Nemotron 3.5 Bolt 74B-A9B, against 164 years running Qwen3 30B-A3B Instruct 2507.
| Nemotron 3.5 Bolt 74B-A9B | Qwen3 30B-A3B Instruct 2507 | |
|---|---|---|
| Intelligence index | 21 | 10 |
| Class | Haiku-class | Below every hosted tier |
| Weights | 22 GB | 19 GB |
| Needs at 32k | 22 GB | 22 GB |
| Quantisation | IQ2 | Q4_K_M |
| Parameters | 74.9B (9B active) | 30.5B (3.3B active) |
| Max context | 256k | 256k |
| API price per 1M | $0.3 in / $2 outpriced as Qwen3.6 27B | $0.048 in / $0.193 out |
| Licence | OpenMDW 1.1 | Apache 2.0 |
| Machines here that run it | 28 of 37 | 28 of 37 |
| Cheapest machine that runs it | Strix Halo Framework Desktop, 32GB $1,269 | Strix Halo Framework Desktop, 32GB $1,269 |
Run Nemotron 3.5 Bolt 74B-A9B on the Framework Desktop, 32GB · or Qwen3 30B-A3B Instruct 2507
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.
| Nemotron 3.5 Bolt 74B-A9B | Qwen3 30B-A3B Instruct 2507 | |
|---|---|---|
| Speed at 32k | 48 tok/s estimated | 27 tok/s estimated |
| Pay-back on this machine | Pays back in 17 years | Pays back in 164 years |
| API cost per month | $6.18priced as Qwen3.6 27B | $0.87 |
Run Nemotron 3.5 Bolt 74B-A9B on the Framework Desktop, 32GB · or Qwen3 30B-A3B Instruct 2507
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. Nemotron 3.5 Bolt 74B-A9B 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 | Nemotron 3.5 Bolt 74B-A9B | Qwen3 30B-A3B Instruct 2507 |
|---|---|---|
| 50ka few chats a day | 175 years | 1,635 years |
| 200klight assistant use | 44 years | 409 years |
| 1Ma moderate coding-assistant day | 8.7 years | 82 years |
| 4Mheavy coding with an agent | 2.2 years | 20 years |
| 20Magents running most of the day | 5.2 months | 4.1 years |
Run Nemotron 3.5 Bolt 74B-A9B at 20M tokens a day · or Qwen3 30B-A3B Instruct 2507
Memory is not what separates them
Nemotron 3.5 Bolt 74B-A9B needs 22 GB of memory at 32k of context and Qwen3 30B-A3B Instruct 2507 needs 22 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.
Nemotron 3.5 Bolt 74B-A9B is also head to head with Qwen3.6 27B above it on the leaderboard and Qwen3.6 35B-A3B below it. One more model needs much the same memory: Qwen3-Coder 30B-A3B. Qwen3 30B-A3B Instruct 2507 is also head to head with Mistral Small 4 (119B-2603) above it on the leaderboard and Qwen3-Coder 30B-A3B, the current Qwen nearest it in size.
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 Nemotron 3.5 Bolt 74B-A9B · every machine that runs Qwen3 30B-A3B Instruct 2507 · every other match-up · both against the frontier · the quickest pay-back at each level of use