正在加载视频...

视频加载失败

返回首页

Omarchy will be a beautiful home. Local AI

0xSero's profile picture

0xSero

67,468 subscribers

27,805 次观看 • 2 天前 •via X (Twitter)

科学技术
LIVE

Anya Rossi• Live Now

Private livecam show

13 条评论

Eric Schleicher 的头像
Eric Schleicher2 天前

Seems like @openchamber_dev should be a natural choice for turnkey local agent tool.

Ameed Jamous (AJ) 的头像
Ameed Jamous (AJ)1 天前

@NixFred For those who are uncomfortable granting remote AI agents access to their personal operating system, consider using Local AI. #omarchy

Steve 的头像
Steve2 天前

It is.. it makes you wonder why something like this took so long

GARY OAKENSHIELD 的头像
GARY OAKENSHIELD2 天前

I just had grok add mine to my agents launcher list

Proton 的头像
Proton1 天前

I will have to explore this soon enough.

Android 的头像
Android2 天前

Looks legit, can you make it bad ass so it chooses the inference server and top trending models based (Hugging Face) on the hardware to maximize the performance and success rate? To save time for the user? Pick your best available model (inference server included) for your PC.

BullBear.News 的头像
BullBear.News2 天前

local inference plugins for window managers are getting surprisingly smooth

RICARDO WAGLAY 的头像
RICARDO WAGLAY2 天前

@grok what is this

Crystal Phantom 的头像
Crystal Phantom2 天前

Good to see Omarchy being built as a dedicated home for local AI.

rubén -🇻🇦/acc 🇺🇲 的头像
rubén -🇻🇦/acc 🇺🇲2 天前

it's looking great man! lmk if you still need testers

~salmun-nister 的头像
~salmun-nister2 天前

Any plans to support AMD Strix Halo?

Mike Gannotti 的头像
Mike Gannotti2 天前

Omarchy is my new favorite for hosting agents

Shikhar 的头像
Shikhar2 天前

I’ll try this one

相关视频

Local AI will be right in your OS Omarchy, PR up soon.
0:51

Local AI will be right in your OS Omarchy, PR up soon.

0xSero

55,753 次观看 • 18 天前

3 months ago I said local AI will be competitive.
0:40

3 months ago I said local AI will be competitive.

0xSero

103,889 次观看 • 10 天前

Updates coming to omarchy: - multiple gpu configs - more models - track your local usage
0:24

Updates coming to omarchy: - multiple gpu configs - more models - track your local usage

0xSero

28,510 次观看 • 2 天前

Any feedback welcome, finalising a lot of things in local ai
0:59

Any feedback welcome, finalising a lot of things in local ai

0xSero

14,733 次观看 • 2 个月前

AI + Omarchy Linux. Computing is going to be fun.
0:33

AI + Omarchy Linux. Computing is going to be fun.

Spencer Bull

30,857 次观看 • 26 天前

Qwen3.5-262B-REAP-4bit cleans my Downloads for me in like 2 minutes. Local AI, even 10B param models can be so much more than we know how to harness right now. Intelligence is a spectrum, me and my REAPs are on it.
2:15

Qwen3.5-262B-REAP-4bit cleans my Downloads for me in like 2 minutes. Local AI, even 10B param models can be so much more than we know how to harness right now. Intelligence is a spectrum, me and my REAPs are on it.

0xSero

32,853 次观看 • 5 个月前

Here’s everything I’ve learned about Local AI in the last year or so. Grateful to Presidio Bitcoin
41:23

Here’s everything I’ve learned about Local AI in the last year or so. Grateful to Presidio Bitcoin

0xSero

33,852 次观看 • 2 个月前

I'm working with Exo to make local AI viable. I will make sure that: 1. I perfect the recipe for making the best LLM compressions w REAP and 4bit quantisation 2. I will make finding, hosting, optimising and USING LLMs so easy you won't know the difference. Open source must win
2:09

I'm working with Exo to make local AI viable. I will make sure that: 1. I perfect the recipe for making the best LLM compressions w REAP and 4bit quantisation 2. I will make finding, hosting, optimising and USING LLMs so easy you won't know the difference. Open source must win

0xSero

11,881 次观看 • 4 个月前

Local AI can be so good, but you’d need about 12k USD to get it. Then it’s not so great Here’s a Q4 of Qwen3.5-262B-REAP Weights 131GB KVCache 50GB 256,000 context 350 tokens/s prefill warmup 4,000 tokens/s prefill cache 36 tokens/s generation Vision enabled REAP is good
3:10

Local AI can be so good, but you’d need about 12k USD to get it. Then it’s not so great Here’s a Q4 of Qwen3.5-262B-REAP Weights 131GB KVCache 50GB 256,000 context 350 tokens/s prefill warmup 4,000 tokens/s prefill cache 36 tokens/s generation Vision enabled REAP is good

0xSero

88,849 次观看 • 5 个月前

Exo No more worrying about it. Best model best config best harness for your hardware based on local . ai benchmarks just: exo run
3:42

Exo No more worrying about it. Best model best config best harness for your hardware based on local . ai benchmarks just: exo run

0xSero

43,386 次观看 • 2 个月前

The agent os is nearly here, Omarchy is so lit. Working on making Qwen generally available across ampere and blackwell, maybe hopper as well. Year of Linux Desktop. 2 days of progress.
0:51

The agent os is nearly here, Omarchy is so lit. Working on making Qwen generally available across ampere and blackwell, maybe hopper as well. Year of Linux Desktop. 2 days of progress.

0xSero

24,671 次观看 • 25 天前

This beautiful home needed to be raised more than 5 feet to protect it against flooding. The home movers did that and now a new foundation will be added.
0:40

This beautiful home needed to be raised more than 5 feet to protect it against flooding. The home movers did that and now a new foundation will be added.

RWB_American

1,282,405 次观看 • 8 个月前

Here's my current tech stack, why I'm using it. And what I think is happening in the local AI scene. Unfortunately I don't like organising myself so you'll have to put up with my rambling (:
25:42

Here's my current tech stack, why I'm using it. And what I think is happening in the local AI scene. Unfortunately I don't like organising myself so you'll have to put up with my rambling (:

0xSero

23,562 次观看 • 4 个月前

Almost ready, I guess I will finally work on the onboarding experience. I have been using vllm-studio for work all day, this is so good. I legit haven't noticed a single issue with the model, the outputs or even the app's usability. You will have your coding agent at home.
2:15

Almost ready, I guess I will finally work on the onboarding experience. I have been using vllm-studio for work all day, this is so good. I legit haven't noticed a single issue with the model, the outputs or even the app's usability. You will have your coding agent at home.

0xSero

14,320 次观看 • 4 个月前

"Omarchy would not have existed without AI." DHH on how AI actually boosts developer productivity.
0:45

"Omarchy would not have existed without AI." DHH on how AI actually boosts developer productivity.

Amp

57,168 次观看 • 8 个月前

Good to be home for a bit. Beautiful lancashire!
0:27

Good to be home for a bit. Beautiful lancashire!

michael

19,443 次观看 • 8 个月前

Omarchy has bulit-in LocalSend, but its look doesn’t quite fit the system. So I built a new client in Omarchy’s style to make it feel at home. DHH Omasend — a local network file transfer client built on the LocalSend protocol.
0:34

Omarchy has bulit-in LocalSend, but its look doesn’t quite fit the system. So I built a new client in Omarchy’s style to make it feel at home. DHH Omasend — a local network file transfer client built on the LocalSend protocol.

Jason Lee

18,923 次观看 • 7 天前

Extracting and sharing all my AI sessions to OpenSource. We will train our own models e2e, join the revolution. I hope I don't get pawned
1:45

Extracting and sharing all my AI sessions to OpenSource. We will train our own models e2e, join the revolution. I hope I don't get pawned

0xSero

22,406 次观看 • 5 个月前

For those of you wondering what a scrappy home AI rig looks like 192gb VRAM 512gb DDR4 Epyc 7443P Pulling a Max 1600w at peak. This can fit: - MiniMax-M2.5 in 4 bits - 60% of GLM-4.7 at 4 bits - Qwen3-coder-next at full precision - 2x GLM-4.7- Flash Bought for 12k now 18k
0:31

For those of you wondering what a scrappy home AI rig looks like 192gb VRAM 512gb DDR4 Epyc 7443P Pulling a Max 1600w at peak. This can fit: - MiniMax-M2.5 in 4 bits - 60% of GLM-4.7 at 4 bits - Qwen3-coder-next at full precision - 2x GLM-4.7- Flash Bought for 12k now 18k

0xSero

47,340 次观看 • 6 个月前