Ornith 1.5 35B-A3B vs Olmo 3.1 32B Think
Neither Ornith 1.5 35B-A3B nor Olmo 3.1 32B Think has been placed on the intelligence index. Both take the same machine to start: the cheapest here that runs either is the Framework Desktop, 32GB, at $1,269. On it, Ornith 1.5 35B-A3B is about 6.6× quicker: 57 tok/s against 8.6, both estimated from memory bandwidth. At 500k tokens a day the Framework Desktop, 32GB pays for itself in 83 years running Ornith 1.5 35B-A3B, against 101 years running Olmo 3.1 32B Think.
| Ornith 1.5 35B-A3B | Olmo 3.1 32B Think | |
|---|---|---|
| Intelligence index | not placed | not placed |
| Class | not yet placed | not yet placed |
| Weights | 22 GB | 19 GB |
| Needs at 32k | 22 GB | 22 GB |
| Quantisation | Q4_K_M | Q4_K_M |
| Parameters | 36B (3B active) | 32.2B |
| Max context | 256k | 64k |
| API price per 1M | $0.05 in / $0.7 outpriced as Qwen3.6 35B-A3B | $0.1 in / $0.34 outpriced as Gemma 4 31B it |
| Licence | MIT | 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 Ornith 1.5 35B-A3B on the Framework Desktop, 32GB · or Olmo 3.1 32B Think
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.
| Ornith 1.5 35B-A3B | Olmo 3.1 32B Think | |
|---|---|---|
| Speed at 32k | 57 tok/s estimated | 8.6 tok/s estimated |
| Pay-back on this machine | Pays back in 83 years | Pays back in 101 years |
| API cost per month | $1.38priced as Qwen3.6 35B-A3B | $1.75priced as Gemma 4 31B it |
Run Ornith 1.5 35B-A3B on the Framework Desktop, 32GB · or Olmo 3.1 32B Think
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. Ornith 1.5 35B-A3B 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 | Ornith 1.5 35B-A3B | Olmo 3.1 32B Think |
|---|---|---|
| 50ka few chats a day | 830 years | 1,005 years |
| 200klight assistant use | 208 years | 251 years |
| 1Ma moderate coding-assistant day | 42 years | 50 years |
| 4Mheavy coding with an agent | 10 years | 13 years |
| 20Magents running most of the day | 2.1 years | 4.2 yearsits ceiling |
The Framework Desktop, 32GB generates at most 11.8M tokens a day on Olmo 3.1 32B Think, 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 Ornith 1.5 35B-A3B at 20M tokens a day · or Olmo 3.1 32B Think
Memory is not what separates them
Both need 22 GB of memory at 32k of context. 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.
Ornith 1.5 35B-A3B is also head to head with Nemotron 3.5 Bolt 74B-A9B and Olmo 3.1 32B Instruct, which need much the same memory. Olmo 3.1 32B Think is also head to head with Olmo 3.1 32B Instruct, the other Olmo model that 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 Ornith 1.5 35B-A3B · every machine that runs Olmo 3.1 32B Think · every other match-up · both against the frontier · the quickest pay-back at each level of use