based lime 🐇🕳

eth is ww3 network /
zFi is ww3 superdapp /
@z0r0zzz is ww3 dev /
zOrgs are ww3 pfp /

that's why I collect zOrgs

[based lime 🐇🕳 @qlime5]

@ZAMM_DEFI is quietly shipping one of the most innovative onchain infra layers in crypto.

• ERC-6909 core (co-authored by Paradigm)
• Multi-token, NFT-native
• Zero-dev launches
• Transparent LP & orderbook

This isn’t another memepad. This is a new primitive.

[0xSero @0xSero]

State of Local AI #1

———

In lieu of Fable ban.

Here’s the best LLMs of the week to run on your hardware.

—— 4-8gb vram/ram 500$

- Gemma-4-qat https://t.co/UFCmLXVKed I had someone mention it’s very good for subagent stuff

—— 8-16gb vram/ram < 1k usd

- Gemma-12B https://t.co/tc6IBTrbc3 without a doubt the smartest model of its size

—— 16-32gb Apple/Strix halo 1-2k usd

- Diffusion Gemma26B https://t.co/mSaWPFpgXQ

- on 1x 6000 it’s eating up to 600 tok/s
- smallest smart MoE we have
- lots of world knowledge
- easy to run

—— 32-96gb ram/vram (2-10k usd)

- nex-n2-mini https://t.co/EL1ePzwI58 builds on qwen3.6-35B and seems to do really well

- qwopus-27B https://t.co/P1gypZwufi this model topped a lot of our benchmarks at https://t.co/UfoYoOlSIk

—— 384gb vram (10-50K usd)

- https://t.co/AZb0Gtu5P3 23B means it’s close to qwen3.6-27B per token, while also have a lot of specialisation.

- fast inference
- top open weight model on AA

—— 768gb-1TB

- https://t.co/kWzJG2Hjen

Kimi has always been a top player here and their last model cuts speed and cost down by 30%
- great vision support
- first coder model by moonshot

———

Top models:

1. Qwen3.6-35B
2. Qwen3.6-27B
3. Step-3.7-Flash
4. Minimax-M3
5. Deepseek-v4-flash

———

Budget sweet spots:

#1 - 1K usd

Single 3090 / Mac mini / Intel arc b70 / AMD

- Qwen / Gemma

#2 - 5k usd

DGX Spark / Mac m5 max / 4x 3090

- qwen / Gemma step and deepseek flash

#3 - 12k usd

RTX Pro 6000 / Mac Ultra / 2x Spark / 8x 3090

Ds4-flash / step-3.7-Flash and above

#4 - 24k usd

2x 6000 / 2x Mac Ultra / 4x Spark / Mix

Same as above

#5 - 50k usd

4x 6000 / 4x Max Ultra / 12x Spark / 2 H100

Minimax-m3 / nex-n2-pro / step-3.7-flash

#6 - 100k usd

GB300 station / 8x 6000 / 4x H200 / Mix

GLM-5.2 / Kimi-K2.7

———

Let’s keep the Internet free thanks for reading

[Dario De Siena - 🔁 @Dario_Desiena]

INSIDE @R3ORDR ✊🔁

[based lime 🐇🕳 @qlime5]

@z0r0zzz no more need to collect zOrgs?

[Privacy Cash @theprivacycash]

Privacy Cash is live on Ethereum.

After powering $400M+ in private transfers, we’re bringing privacy to Ethereum.

Privacy Cash lets you transfer and bridge funds without linking past addresses or transaction history.

Why use Privacy Cash on Ethereum?👇

[vitalik.eth @VitalikButerin]

Encrypted messaging, like @signalapp, is critical for preserving our digital privacy. Two important next steps for the space are (i) permissionless account creation and (ii) metadata privacy.

@session_app and @SimpleXChat are two messaging apps pushing these directions forward.

For this reason I've donated 128 ETH to each. Addresses available on their websites if you wish to follow on:

https://t.co/07ORUYDCu8
https://t.co/FQde3IK0uz

But also, actually download and use them!

Neither of the two are perfect pieces of software, they have a way to go to get to truly optimal user experience and security. Strong metadata privacy requires decentralization, decentralization is hard, users expecting multi-device support makes everything harder. Sybil / DoS resistance, both in the message routing network and on the user side (without forcing phone number dependence) adds further difficulty.

These problems need more eyes on them. I wish all teams working on these important problems best of luck.

[niko @saintniko]

yeah everything sucks and it feels like it’s over but

it’s actually an awesome time to try apps, so here’s a few I’ve been using lately:

@mnstr
@stompdotgg
@variational_io
@noise_xyz

[ross.wei @z0r0zzz]

eth [ . . . ] btc

[0xflorent.eth @0xFlorent_]

First white-hat exploit on Ethereum: I unlocked 1,003.62
Ξ ($2,000,000) trapped in a 2016 ICO smart contract
for 9 years.

The 48 original investors can now claim their funds.

[based lime 🐇🕳 @qlime5]

@tacitfi ww3fi

[tacit @tacitfi]

Tacit protocol and assets are now supported on UniSat.

[0xSero @0xSero]

Best models I’ve seen this week for your hardware: if you have 8-16gb you have a competitive model finally!

———-

4gb - 8gb:

- minicpm5: this model was built for agentic tool use on tiny machines: https://t.co/LvNnIDSh7u

- tops benchmarks in weight class
- extremely small
- great for using in projects with AI
- blazing fast

————

8gb - 16gb

Most exciting model

- LFM-2.5-8B: https://t.co/5SYi6D56FR

Frontier for vram:

- 8b moe with
- 1.5B active
- trained on 38T tokens (MASSIVE)
- 131k context

————-

96GB - 128GB

- ds4flash either q2 or reap + q4
https://t.co/BaphZfWrwG
- or
https://t.co/EAZB4bDYjA

- very strong agent
- logical pleasant to talk to
- good in Hermes
- fast
- high contexts for little vram

————-

196gb+

Step-3.7-Flash: https://t.co/oaVf5wMILx

- 199B with 11B active (FAST)
- vision support!
- its predecessor was topping benchmarks for 3 months
- 256k context
- 150 tok/s on 6000s

[vitalik.eth @VitalikButerin]

Updates since then:

* Deepseek v4 is out. There *is* a 2-bit quant that can run within 90 GB ( https://t.co/yM1HMZXkXn ), and it works, however it's only fast on Apple hardware (I've head ~35 tok/s). On AMD, it's ~7 tok/s. IMO actually taking the effort to properly support more than one hardware manufacturer is a great example of the difference between mere "decentralized AI" and genuine "CROPS AI". I hope we can become better at this.
* https://t.co/CFYF1smBH3 also has alpha telegram support now. However, the path to adding your account is quite janky
* https://t.co/za4h233eYz looks promising as a way to run "dense" models (eg. Qwen 27B) more efficiently. It's janky, but on my 5090 laptop it seems to be ~2x more tok/s than llama.cpp
* VoxTerm (local AI recording, no third-party servers) continues to be developed https://t.co/GSdKzkD9Ql

And there's a lot more projects coming on the horizon.

One other thing that has been on my mind is that there's actually a lot of intersection between "CROPS ethereum access layer" and "CROPS AI". For example, we want a ZK way to make (paid) calls to remote LLMs. But if we have this, then it's just as useful for solving another problem: private RPC reads in Ethereum.

Another example: application-specific finetuned LLMs. Leanstral ( https://t.co/ilfww8ekJu ; I get ~38 tok/s on AMD) fits into < 70 GB, but can hold its own against 1T models on writing Lean code. Things like this are a huge boon for writing more secure code ( https://t.co/6YPWgVSzCg ). We should have models finetuned for Ethereum-related use cases as well.

[Figure31 @figure31]

After two years of work, I’m proud to present DEL.

256 on-chain animated artworks,
bodies for the Ethereum network.

Dynamic and shaped by their owners.

Private mint: May 27
Public mint: May 30
0.1 ETH

Explore the series → https://t.co/b67O5qcJFY

[ross.wei @z0r0zzz]

tETH is the first trustless bridge to Bitcoin. And also the first mixer bridge that shields you every step of the way.

[ross.wei @z0r0zzz]

tacit tech can shield bitcoin and ethereum users, with same trust assumptions as their native chains

soon, tacit defi will include AMM and LP

you might never need to leave, but you always can. And that's the point.

[ross.wei @z0r0zzz]

trustless ETH-Bitcoin bridge with SP1 zk proofs

added benefit: works as mixer to shield all users

👍 #tETH

[tacit @tacitfi]

privacy mode: shielded BTC and tacit sends unlocked

[based lime 🐇🕳 @qlime5]

@hantengri $tacit: 0 VCs, tacit mcap $5M, annual revenue: TBD.
settles on Bitcoin L1. made by trusted known dev.

you should check it buddy @tacitfi @z0r0zzz

[based lime 🐇🕳 @qlime5]

@hantengri $tacit: 0 VCs, tacit mcap $5M, annual revenue: TBD.
settles on Bitcoin L1. made by trusted known dev.

you should check it buddy @tacitfi @z0r0zzz

[based lime 🐇🕳 @qlime5]

@binji_x I would be lucky to join