Alex Firsov

co-founder @fortytwo

[Alex Firsov @thisisfirsov]

Nemotron just got swarmed

• 40% higher scores on DeepSWE
• 80% fewer tokens per run on IFBench

Try it for free now:
https://t.co/c68K4ROgqx

[Fortytwo @fortytwo]

Nemotron 3.5 Super VL is live on Fortytwo Engine

Same weights, turbocharged by Swarm Inference:

• Up to 45% higher scores on select benchmarks
• Up to 80% higher token efficiency per task

Available for free: https://t.co/Wm57NUE283

[Alex Firsov @thisisfirsov]

It's been a tough week

Support open models

Use Nemotron

It's free: https://t.co/c68K4ROgqx

[Prey.gdp @PreyWebthree]

Same model weights. Smarter inference. Better results.

@fortytwo Engine is showing how Swarm Inference can push the capabilities of existing AI models even further.

Up to 45% higher scores on select benchmarks and up to 80% greater token efficiency per task. A genuinely impressive step forward.

Making this technology freely accessible creates an opportunity for everyone to experience it firsthand.

👇 Try it now: https://t.co/OMh7SpQS0u

[Alex Firsov @thisisfirsov]

Nemotron just got swarmed

• 40% higher scores on DeepSWE
• 80% fewer tokens per run on IFBench

Try it for free now:
https://t.co/c68K4ROgqx

[Alex Firsov @thisisfirsov]

@AnakiTech @fortytwo True

[Wonder of Science @wonderofscience]

The collective intelligence of ants solving the “piano movers” puzzle.

📽️: Dreyer et al., PNAS 2025

[Alex Firsov @thisisfirsov]

Wait, what?

[Fortytwo @fortytwo]

We’ve cut Qwen3.8 27B pricing by 80%

Qwen3.8 27B on Engine:

• Up to 13% higher benchmark scores
• Up to 25% fewer tokens per task

Get your API key: https://t.co/Wm57NUE283

[Mar @Mar_dc8]

Pelican riding a bicycletest using the improved Qwen 3.8 27B powered by @fortytwo engine vs vanilla Qwen 3.8 27B

The improvement is insane, I'm shocked

You can try @fortytwo for free here: https://t.co/Bjz96HobN7

[Alex Firsov @thisisfirsov]

swarm augmented Qwen3.8 27B is free today on https://t.co/c68K4ROgqx

[mimie @0xMimie]

swarm augmented Qwen3.8 27B is free today on https://t.co/m1iJQuOUxh

[Vlad Larin @vlarin]

the best Qwen3.8-27B is free today

[Alex Firsov @thisisfirsov]

Try it!

[Fortytwo @fortytwo]

Qwen3.8-27B is free on Fortytwo Engine for 24 hours.

Same model. Swarm inference on top.

Starts today at 12:00 UTC.
Any task, any volume, no card.

Get an API key and point your agent at it:
https://t.co/Wm57NUE283

[Alex Firsov @thisisfirsov]

1b+ tokens were processed on Fortytwo Engine in the last 24 hours

[Alex Firsov @thisisfirsov]

1b+ tokens were processed on Fortytwo Engine this week

[Alex Firsov @thisisfirsov]

1b+ tokens were processed on Fortytwo Engine this week

[mimie @0xMimie]

if you're building with AI you should check @fortytwo

[Fortytwo @fortytwo]

Fortytwo Engine more than doubled Qwen3.8-27B’s score on @scaling01's LisanBench

Standalone BF16: 2,452
Fortytwo Engine swarm: 5,197 (+112%)

LisanBench tests strategic planning, memory and constraint following: build the longest word chain possible using single-letter edits, dictionary words and no repeats.

Both runs: 50 starting words × 3 trials, temperature 1.0, 100k-token cap, xhigh reasoning, leaderboard scoring.

What improved:
• Repetition loops observed in the standalone run; none observed on Engine
• Higher mean scores on 40/50 starting words
• Mean link validity: 92.2% → 97.1%
• Fully valid chains: 5.6% → 22.9% of recorded answers
• Answers after retries: 72/150 → 140/150

Against the October 16 leaderboard, these scores would place 28th → 14th, putting Qwen3.8-27B on Fortytwo Engine between GPT 5.4 (medium) and DeepSeek V3.2 Speciale.

These are our runs, not official leaderboard entries.

[Alex Firsov @thisisfirsov]

imagine a swarm of Qwens reasoning together to deliver more accurate answers than one Qwen alone at a lower cost per task

that’s already live on Fortytwo Engine

[Fortytwo @fortytwo]

Introducing Fortytwo Engine

An inference API that runs open-weight models through Swarm Inference

• 7% higher scores on average vs. the base model
• Nearly 25% fewer tokens per task
• Same per-token price and speed
• Private by default

First model: Qwen3.8-27B
Try it: https://t.co/zIiOKnxZSS

[Fortytwo @fortytwo]

Qwen3.8-27B by @Alibaba_Qwen is now live on Fortytwo Engine.

Same model, with better answers:

• 24.7% fewer tokens per run
• DeepSWE: +13% accuracy
• GDP.pdf: +11.4% accuracy
• Same per-token price and speed

Test it on your own tasks:
https://t.co/Wm57NUE283

[Keone Hon @keoneHD]

Swarm Inference 🤖

[James @_jhunsaker]

try it

[Fortytwo @fortytwo]

Introducing Fortytwo Engine

An inference API that runs open-weight models through Swarm Inference

• 7% higher scores on average vs. the base model
• Nearly 25% fewer tokens per task
• Same per-token price and speed
• Private by default

First model: Qwen3.8-27B
Try it: https://t.co/zIiOKnxZSS