Nemotron 3.5 Lightning 30B-A3B vs Flint 40B-A2.5B
Nemotron 3.5 Lightning 30B-A3B scores 14 on the intelligence index, and Flint 40B-A2.5B has not been placed on it. Both take the same machine to start: the cheapest here that runs either is the Radeon AI PRO R9700, 32GB, at $1,299. The Radeon AI PRO R9700, 32GB is priced as the card alone, without the PC around it. On it, they run at much the same speed: 127 and 131 tok/s, both estimated from memory bandwidth. At 500k tokens a day the Radeon AI PRO R9700, 32GB pays for itself in 85 years running Flint 40B-A2.5B, against 297 years running Nemotron 3.5 Lightning 30B-A3B.
| Nemotron 3.5 Lightning 30B-A3B | Flint 40B-A2.5B | |
|---|---|---|
| Intelligence index | 14 | not placed |
| Class | Below every hosted tier | not yet placed |
| Weights | 25 GB | 25 GB |
| Needs at 32k | 26 GB | 26 GB |
| Quantisation | Q4_K_M | UD-Q4_K_XL |
| Parameters | 31.6B (3B active) | 39.8B (2.5B active) |
| Max context | 256k | 256k |
| API price per 1M | $0.025 in / $0.12 out | $0.05 in / $0.7 outpriced as Qwen3.6 35B-A3B |
| Licence | OpenMDW 1.1 | Apache 2.0 |
| Machines here that run it | 27 of 37 | 27 of 37 |
| Cheapest machine that runs it | AMD Radeon AI PRO R9700, 32GB $1,299card only | AMD Radeon AI PRO R9700, 32GB $1,299card only |
Run Nemotron 3.5 Lightning 30B-A3B on the Radeon AI PRO R9700, 32GB · or Flint 40B-A2.5B
Jump to: Side by side on the Radeon AI PRO R9700, 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 Radeon AI PRO R9700, 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: AMD Radeon AI PRO R9700, 32GB, at $1,299card only.
| Nemotron 3.5 Lightning 30B-A3B | Flint 40B-A2.5B | |
|---|---|---|
| Speed at 32k | 127 tok/s estimated | 131 tok/s estimated |
| Pay-back on this machine | Pays back in 297 years | Pays back in 85 years |
| API cost per month | $0.47 | $1.38priced as Qwen3.6 35B-A3B |
Run Nemotron 3.5 Lightning 30B-A3B on the Radeon AI PRO R9700, 32GB · or Flint 40B-A2.5B
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. Flint 40B-A2.5B 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 Lightning 30B-A3B | Flint 40B-A2.5B |
|---|---|---|
| 50ka few chats a day | 2,968 years | 848 years |
| 200klight assistant use | 742 years | 212 years |
| 1Ma moderate coding-assistant day | 148 years | 42 years |
| 4Mheavy coding with an agent | 37 years | 11 years |
| 20Magents running most of the day | 7.4 years | 2.1 years |
Run Nemotron 3.5 Lightning 30B-A3B at 20M tokens a day · or Flint 40B-A2.5B
Memory is not what separates them
Nemotron 3.5 Lightning 30B-A3B needs 26 GB of memory at 32k of context and Flint 40B-A2.5B needs 26 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 Lightning 30B-A3B is also head to head with Qwen3.5 9B above it on the leaderboard and Qwen3 235B-A22B Instruct 2507 below it. Flint 40B-A2.5B is also head to head with Granite 4.2 30B, which needs much the same memory.
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 Lightning 30B-A3B · every machine that runs Flint 40B-A2.5B · every other match-up · both against the frontier · the quickest pay-back at each level of use