DeepSeek V4-Flash vs Inkling Small
DeepSeek V4-Flash scores higher on the intelligence index, 35 against 26. Both take the same machine to start: the cheapest here that runs either is the Mac Studio M5 Ultra, 256GB, at $10,799. On it, DeepSeek V4-Flash is about 1.1× quicker: 49 tok/s against 43, both estimated from memory bandwidth. At 500k tokens a day the Mac Studio M5 Ultra, 256GB pays for itself in 124 years running Inkling Small, against 1,736 years running DeepSeek V4-Flash.
| DeepSeek V4-Flash | Inkling Small | |
|---|---|---|
| Intelligence index | 35 | 26 |
| Class | Sonnet-class | Haiku-class |
| Weights | 155 GB | 163 GB |
| Needs at 32k | 155 GB | 164 GB |
| Quantisation | UD-Q4_K_M | UD-Q4_K_M |
| Parameters | 284B (13B active) | 266B (12B active) |
| Max context | 1M | 1M |
| API price per 1M | $0.04732 in / $0.09464 out | $0.45 in / $1.2 out |
| Licence | MIT | Apache 2.0 |
| Machines here that run it | 1 of 37 | 1 of 37 |
| Cheapest machine that runs it | Mac Studio M5 Ultra, 256GB $10,799 | Mac Studio M5 Ultra, 256GB $10,799 |
Run DeepSeek V4-Flash on the Mac Studio M5 Ultra, 256GB · or Inkling Small
Jump to: Side by side on the Mac Studio M5 Ultra, 256GB · 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 Mac Studio M5 Ultra, 256GB
The cheapest machine that runs either model is the same one, so this is the pair doing the same work on the same hardware: Mac Studio M5 Ultra, 256GB, at $10,799.
| DeepSeek V4-Flash | Inkling Small | |
|---|---|---|
| Speed at 32k | 49 tok/s estimated | 43 tok/s estimated |
| Pay-back on this machine | Pays back in 1,736 years | Pays back in 124 years |
| API cost per month | $0.77 | $7.56 |
Run DeepSeek V4-Flash on the Mac Studio M5 Ultra, 256GB · or Inkling Small
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 Mac Studio M5 Ultra, 256GB. Inkling Small 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 | DeepSeek V4-Flash | Inkling Small |
|---|---|---|
| 50ka few chats a day | 17,360 years | 1,236 years |
| 200klight assistant use | 4,340 years | 309 years |
| 1Ma moderate coding-assistant day | 868 years | 62 years |
| 4Mheavy coding with an agent | 217 years | 15 years |
| 20Magents running most of the day | 43 years | 3.1 years |
Run DeepSeek V4-Flash at 20M tokens a day · or Inkling Small
Memory is not what separates them
DeepSeek V4-Flash needs 155 GB of memory at 32k of context and Inkling Small needs 164 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.
DeepSeek V4-Flash is also head to head with Qwen3.8 Flash Next above it on the leaderboard and Qwen3.8 27B below it. One more model needs much the same memory: MiniMax M2.7. Inkling Small is also head to head with Beam 1.0 501B-A23B above it on the leaderboard and Tencent Hy3 below it.
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 DeepSeek V4-Flash · every machine that runs Inkling Small · every other match-up · both against the frontier · the quickest pay-back at each level of use