LFM2.5 2.6B vs Raon-1 nano
LFM2.5 2.6B scores 8 on the intelligence index, and Raon-1 nano has not been placed on it. Both take the same machine to start: the cheapest here that runs either is the Mac mini M6, 16GB, at $899. On it, LFM2.5 2.6B is about 1.4× quicker: 52 tok/s against 37, both estimated from memory bandwidth. At 500k tokens a day the Mac mini M6, 16GB pays for itself in 14 years running LFM2.5 2.6B, against 81 years running Raon-1 nano.
| LFM2.5 2.6B | Raon-1 nano | |
|---|---|---|
| Intelligence index | 8 | not placed |
| Class | Below every hosted tier | not yet placed |
| Weights | 1.7 GB | 2.1 GB |
| Needs at 32k | 2.2 GB | 2.3 GB |
| Quantisation | Q4_K_M | Q4_K_M |
| Parameters | 2.7B | 3.1B (1.5B active) |
| Max context | 128k | 256k |
| API price per 1M | $0.35 in / $0.5 out | $0.06 in / $0.15 outpriced as Granite 4.2 8B |
| Licence | LFM 1.0 (see repo) | Apache 2.0 |
| Machines here that run it | 37 of 37 | 37 of 37 |
| Cheapest machine that runs it | Mac mini M6, 16GB $899 | Mac mini M6, 16GB $899 |
Run LFM2.5 2.6B on the Mac mini M6, 16GB · or Raon-1 nano
Jump to: Side by side on the Mac mini M6, 16GB · 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 mini M6, 16GB
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 mini M6, 16GB, at $899.
| LFM2.5 2.6B | Raon-1 nano | |
|---|---|---|
| Speed at 32k | 52 tok/s estimated | 37 tok/s estimated |
| Pay-back on this machine | Pays back in 14 years | Pays back in 81 years |
| API cost per month | $5.47 | $1.00priced as Granite 4.2 8B |
Run LFM2.5 2.6B on the Mac mini M6, 16GB · or Raon-1 nano
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 mini M6, 16GB. LFM2.5 2.6B 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 | LFM2.5 2.6B | Raon-1 nano |
|---|---|---|
| 50ka few chats a day | 138 years | 814 years |
| 200klight assistant use | 35 years | 204 years |
| 1Ma moderate coding-assistant day | 6.9 years | 41 years |
| 4Mheavy coding with an agent | 21 months | 10 years |
| 20Magents running most of the day | 4.2 months | 2.0 years |
Run LFM2.5 2.6B at 20M tokens a day · or Raon-1 nano
Memory is not what separates them
LFM2.5 2.6B needs 2.2 GB of memory at 32k of context and Raon-1 nano needs 2.3 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.
LFM2.5 2.6B is also head to head with Llama 3.3 70B Instruct above it on the leaderboard and Devstral Small 2 24B 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 LFM2.5 2.6B · every machine that runs Raon-1 nano · every other match-up · both against the frontier · the quickest pay-back at each level of use