Pinned Tweet
Today we're releasing Underdog Saluki 27B
Based on Qwen 3.8 27B, Saluki is almost 7x smaller than its full-precision counterpart while it keeps 96% of its benchmark performance and beats Qwen at tool calling
It's the best model <8GB that runs in Underdog
Saluki is available today under Apache 2.0. Try today in Underdog underdog.ai/saluki
bro wants to charge u a subscription, train on ur data, then sell u ads
big ai hates underdog. don’t believe the psyop
sam: local inference is a terrible allocation of scarce resources
“a lot of people want local inference, and somehow they assume that the problem is solved now because we have open-source models, we're going to be able to run them on our computers, and so we're not going to need all the stuff in the data centre
but from a global allocation perspective, actually it's quite terrible to have everybody, like, have a bunch of the world's limited supply of DRAM sitting in their own computer and being used five percent of the time
you want maximum utilisation in the cloud if you're trying to deal with this very supply-constrained environment
somehow many people's intuition is the opposite of that”
“Underdog AI is doing wonders with my ancient 16GB m1 pro Mac”
seeing a happy owner makes me happy
Replying to @UnderdogAI
@UnderdogAI about to replace my subscriptions
As someone who doesn't have unlimited money to get 128GB of RAM, Underdog AI is doing wonders with my ancient 16GB m1 pro Mac. Coding will be the next test!
@0xSigil
“Underdog is doing wonders with my ancient 16GB m1 pro Mac” - happy owner 🩵🦴
Replying to @UnderdogAI
@UnderdogAI about to replace my subscriptions
As someone who doesn't have unlimited money to get 128GB of RAM, Underdog AI is doing wonders with my ancient 16GB m1 pro Mac. Coding will be the next test!
@0xSigil
Underdog AI retweeted
Replying to @UnderdogAI
@UnderdogAI about to replace my subscriptions
As someone who doesn't have unlimited money to get 128GB of RAM, Underdog AI is doing wonders with my ancient 16GB m1 pro Mac. Coding will be the next test!
@0xSigil
get your smart Underdog a smart dog house 💻
All AI should be free, so I’m giving away the first RTX laptop for free, signed by NVIDIA Founder
@UnderdogAI gives everyone a free, capable & private AI. 100% on-device
To enter:
1) Retweet and like this post
2) Sign up for Underdog giveaway: underdog.ai/spark
3) follow @UnderdogAI so we can dm u
I CAN FINALLY CANCEL MY CHATGPT AND CLAUDE SUBSCRIPTIONS. Thank you @underdogai. Entered to win their signed RTX Spark
nitter.cf/0xSigil/status/2114930…
All AI should be free, so I’m giving away the first RTX laptop for free, signed by NVIDIA Founder
@UnderdogAI gives everyone a free, capable & private AI. 100% on-device
To enter:
1) Retweet and like this post
2) Sign up for Underdog giveaway: underdog.ai/spark
3) follow @UnderdogAI so we can dm u
All AI should be free, so I’m giving away the first RTX laptop for free, signed by NVIDIA Founder
@UnderdogAI gives everyone a free, capable & private AI. 100% on-device
To enter:
1) Retweet and like this post
2) Sign up for Underdog giveaway: underdog.ai/spark
3) follow @UnderdogAI so we can dm u
Underdog Saluki 27B has been downloaded 500k times.
Today we're releasing Underdog Saluki 27B
Based on Qwen 3.8 27B, Saluki is almost 7x smaller than its full-precision counterpart while it keeps 96% of its benchmark performance and beats Qwen at tool calling
It's the best model <8GB that runs in Underdog
Saluki is available today under Apache 2.0. Try today in Underdog underdog.ai/saluki
Underdog AI retweeted
Replying to @UnderdogAI
@UnderdogAI is a very impressive piece of local AI. Soon all desktop apps will rely on having a local model they can ask anything they want.
Underdog is the AI for all my missing subscriptions, or any time I want privacy. Its meeting transcripts can be a lifesaver.
And its meeting notes are just as useful as the unicorns in this space!
(equally useless)
0 setup, 0 cost, 0 wifi, smart AI on your Phone
Go Underdog, Go hacks- free: underdog.ai/ios
This is serious. you gotta protect yourself from hacks
No Cloud agents, No WIFI is needed to run AI on Underdog
Get offline intelligence on your iPhone today: underdog.ai/ios
I just tried this out
it's indeed really really fast
Today we’re releasing Underdog Bark 3.0, the #1 frontier speech model
It's a tiny 163 MB download as accurate as NVIDIA’s Parakeet (15x bigger). It beats OpenAI's Whisper large-v3 (57x bigger)
It's fast- transcribes 1 min of audio in <0.25s on a Macbook. On recorded meetings (AMI), Bark 3.0 gets 7.82% of words wrong. Parakeet gets 9.42%. OpenAI's Whisper large-v3 gets 13.63% error rate
Bark runs on both your Laptop & Phone. It’s free and open source under CC-BY 4.0
Try private on-device meeting notes & dictation, powered by Bark, in Underdog today: underdog.ai/bark
Underdog AI retweeted
おー、163MBでこの性能は気になるから公開されたら日本語で試してみたい
Underdogちゃんかわいいよぉ
Today we’re releasing Underdog Bark 3.0, the #1 frontier speech model
It's a tiny 163 MB download as accurate as NVIDIA’s Parakeet (15x bigger). It beats OpenAI's Whisper large-v3 (57x bigger)
It's fast- transcribes 1 min of audio in <0.25s on a Macbook. On recorded meetings (AMI), Bark 3.0 gets 7.82% of words wrong. Parakeet gets 9.42%. OpenAI's Whisper large-v3 gets 13.63% error rate
Bark runs on both your Laptop & Phone. It’s free and open source under CC-BY 4.0
Try private on-device meeting notes & dictation, powered by Bark, in Underdog today: underdog.ai/bark
Today we’re releasing Underdog Bark 3.0, the #1 frontier speech model
It's a tiny 163 MB download as accurate as NVIDIA’s Parakeet (15x bigger). It beats OpenAI's Whisper large-v3 (57x bigger)
It's fast- transcribes 1 min of audio in <0.25s on a Macbook. On recorded meetings (AMI), Bark 3.0 gets 7.82% of words wrong. Parakeet gets 9.42%. OpenAI's Whisper large-v3 gets 13.63% error rate
Bark runs on both your Laptop & Phone. It’s free and open source under CC-BY 4.0
Try private on-device meeting notes & dictation, powered by Bark, in Underdog today: underdog.ai/bark
Bringing more models on device- smaller and smarter @UnderdogAI 🐶
Love seeing what @UnderdogAI is bringing to RTX Spark. Their Saluki 27B model brings fast, private personal AI to your laptop in under 8GB of memory. 👏


















