Dolphin

AI Lab developing uncensored models & distributed inference ⟠ Over 5m monthly downloads on Hugging Face ⟠

[Dolphin @dphnAI]

Qwen 3.6 35B data generation on Dolphin Network

22.8 billion tokens generated
383 GPUs online right now
24.33 TB of aggregate vRAM

Equivalent to over 300 H100s worth of idle GPU memory repurposed for inference

https://t.co/Wwpy7eKHX9

[Dolphin @dphnAI]

Node provider rollout has been going well

Our pool of inference nodes running Qwen 3.6 35B have generated over 3.2B tokens so far

Total inference bandwidth -> 9400 t/s

28x RTX 4090
12x RTX 5090
8x RTX PRO 6000
& many other cards

API access coming soon 🐬

[Fahd Mirza @fahdmirza]

🐬 Dolphin X1 Trinity Nano is HERE and it answers EVERYTHING

🔓 Built with a first-of-its-kind RL de-alignment pipeline — no hedging, no lectures, no dad advice

🔹 100% benchmark response rate vs GPT-5 at 11% and Gemini 2.5 Pro at 24%
🔹 Multi-gate, multi-judge reward system that blocks every escape route
🔹 Runs fully local on vLLM — your data never leaves your machine
🔹 Perfect for red teamers, security researchers and AI safety teams

🔥 Watch the full video below 👇

https://t.co/zbCb1zYEIL

[Dolphin @dphnAI]

We have also released a blog post that goes into detail on the RL environment design, as well as the challenges we encountered along the way

https://t.co/3Z3kQAU2BN

You can also try it for free in our Web UI at https://t.co/XqmguUlPxs

[Dolphin @dphnAI]

Dolphin X1 Trinity Nano is now live on @huggingface

Our smallest decensored model yet - 6B MoE with 1B active parameters trained using only online RL

Huge thanks to @TargonCompute for providing an 8xB200 node, @PrimeIntellect for hosted RL, and @arcee_ai for the Trinity series

[Dolphin @dphnAI]

You can download the model today on Hugging Face and run Q8_0 with a 32K context on just 8GB of VRAM

It can even run on mobile devices

Full weights
https://t.co/bvWOhTE0iz

GGUF
https://t.co/nSPQaoBvv7

FP8
https://t.co/qZLx3mzcsb

[doc🃏 @jkrdoc]

https://t.co/VJR5VQbAVx

[Dolphin @dphnAI]

@Uniswap @RAILGUN_Project @aztecnetwork @HastraFi @MascotAsteroid Thanks for mentioning $POD

Protocol-owned Uniswap v4 1% liquidity pools are a great way for early-stage projects to fund development

[Dolphin @dphnAI]

@jkrdoc Nice article sir, very well researched

[Dolphin @dphnAI]

@direkturcrypto Today ☃️

[Dolphin @dphnAI]

First epoch of rewards for node providers has been paid out

50K $POD distributed to 33 providers based on relative contributions to the Qwen 35B inference pool

https://t.co/Wwpy7eKHX9

[Dolphin @dphnAI]

Node provider rollout has been going well

Our pool of inference nodes running Qwen 3.6 35B have generated over 3.2B tokens so far

Total inference bandwidth -> 9400 t/s

28x RTX 4090
12x RTX 5090
8x RTX PRO 6000
& many other cards

API access coming soon 🐬

[Dolphin @dphnAI]

@zacxbt @baseapp $POD is the ticker - we migrated 1:1 from $DPHN

[Dolphin @dphnAI]

We have a new paper on model weight proofs that run on every request inside the inference engine releasing soon

In v1, we were relying on logprobs to verify the correct model is loaded via the expected fingerprint

Alongside slashable bonds for operators, i’d argue that was already very strong but it will be greatly improved in v2 which we are releasing within a month

For v2, we don’t have to rerun inference on a validator GPU in the same way you have to with logprobs - instead we have proofs that can be validated very quickly on a CPU with less overhead

Preview of benchmarks attached

[Dolphin @dphnAI]

@0xmons Was referring to the base model made by Mistral linked above

Still a very popular model despite being a few months old

[Dolphin @dphnAI]

@0xmons This was built on Mistral small 3.2 vision, the updated version - still has 870k monthly downloads

Have a bunch of new models we have been working on that will be releasing soon

https://t.co/X34GlLYov1

[jesse.base.eth @jessepollak]

a decentralized inference network seems powerful

[Dolphin @dphnAI]

https://t.co/1bpa2Y6vox

[Dolphin @dphnAI]

@lucaxyzz Guide at https://t.co/jfPki95ZoU

RTX 6000 PRO can participate now in running Qwen 3.6 35B

Support for smaller GPUs coming soon

You can watch the network stats live at https://t.co/Wwpy7eKHX9

[Dolphin @dphnAI]

@_0xghost_ @FoFan_eth @AskVenice dm sir, will send you the deck

Currently updating website with new docs

[jesse.base.eth @jessepollak]

@AntSeedAI and this from @dphnAI

[Dolphin @dphnAI]

@0x_bzzz @0xJeff We verify node operators are running the expected model by comparing logprobs + tokenised output to validators & a bunch of other techniques