0xSero's banner
0xSero's profile picture

0xSero

@0xSero • 58,033 subscribers

I want to be free

Shorts

Codex nooooooo I can't close this popup

Codex nooooooo I can't close this popup

135,833 views

What 4 concurrency on GLM sounds like. So gosh damn loud, open air frames are easier to build but so gosh darn loud

What 4 concurrency on GLM sounds like. So gosh damn loud, open air frames are easier to build but so gosh darn loud

11,809 views

GLM-5.2-REAP-NVFP4 This experiment I calibrated the model on 30,000+ samples of my agent sessions, tweets, writing, and codebases. Pretty charming, every dataset produced something different.

GLM-5.2-REAP-NVFP4 This experiment I calibrated the model on 30,000+ samples of my agent sessions, tweets, writing, and codebases. Pretty charming, every dataset produced something different.

22,535 views

The fact that a 284B parameter model is able to in a single 400K token session - ssh into my Homelab to find docs - ssh into lambda / prime intellect - rewrite reap to support the DS4 attention - download models & datasets - run tests to check it works

The fact that a 284B parameter model is able to in a single 400K token session - ssh into my Homelab to find docs - ssh into lambda / prime intellect - rewrite reap to support the DS4 attention - download models & datasets - run tests to check it works

22,762 views

Asking Codex (GPU) to find and kill Codex (Cerebras)

Asking Codex (GPU) to find and kill Codex (Cerebras)

24,131 views

Videos

LIVE
1.2k

Anya Rossi

sweetdream.ai

SweetDream.aiSponsored•Livecam
Streaming Now

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

HD live stream
Exclusive private shows
1.2k viewers online

Free preview available • Premium content

GLM-5.2 Nvidia NVFP4 No pruning, no quantising, exact same model card. 110 tok/s single stream. My friend is a genius, holy fudge. Here's the repo, he got full DS4-Flash on a 5090 + DDR5 at 38.5 tok/s This is a breakthrough.
0:28
0xSero's profile picture

GLM-5.2 Nvidia NVFP4 No pruning, no quantising, exact same model card. 110 tok/s single stream. My friend is a genius, holy fudge. Here's the repo, he got full DS4-Flash on a 5090 + DDR5 at 38.5 tok/s This is a breakthrough.

0xSero

155,785 views • 10 days ago

GLM-5.2 on 4x 6000s in ZCode /goal build a nintendo ds emulator in C++, do not use a ready made emulator. Don't stop until you can run the Mario 64 DS rom.
0:46
0xSero's profile picture

GLM-5.2 on 4x 6000s in ZCode /goal build a nintendo ds emulator in C++, do not use a ready made emulator. Don't stop until you can run the Mario 64 DS rom.

0xSero

38,993 views • 12 days ago

Kimi IS COOKING holy mackerel this is way better than anything I can get out of opus or GPT Has some bugs.. but looks soooo unique and well into my brand, for 1 shot I can't complain.
0:41
0xSero's profile picture

Kimi IS COOKING holy mackerel this is way better than anything I can get out of opus or GPT Has some bugs.. but looks soooo unique and well into my brand, for 1 shot I can't complain.

0xSero

235,591 views • 5 months ago

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
0xSero's profile picture

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 views • 1 month ago

. is continuing to grow and improve, it's gotten to a place where I'm very proud of it. Now to release it.
2:14
0xSero's profile picture

. is continuing to grow and improve, it's gotten to a place where I'm very proud of it. Now to release it.

0xSero

11,221 views • 7 days ago

I promise this is the last pleometric video I drop on you.
1:04
0xSero's profile picture

I promise this is the last pleometric video I drop on you.

0xSero

131,800 views • 3 months ago

Here's my conversation with Philip Kiely. A deep dive into inference engineering, his book his available online for free, and it's worth reading. Inference is becoming more important to people and organisations by the day, learning about the topic will prepare you well.
53:53
0xSero's profile picture

Here's my conversation with Philip Kiely. A deep dive into inference engineering, his book his available online for free, and it's worth reading. Inference is becoming more important to people and organisations by the day, learning about the topic will prepare you well.

0xSero

24,290 views • 18 days ago

It's not a dream anymore, this is frontier at home. My next mission is to make this cheaper to run. Do you see the length of the session? Do you see the successful tool calls?
0:27
0xSero's profile picture

It's not a dream anymore, this is frontier at home. My next mission is to make this cheaper to run. Do you see the length of the session? Do you see the successful tool calls?

0xSero

31,883 views • 24 days ago

If you're a frontend dev let me make your life easier: 1. Pay for mobbin. 2. Setup mobbin MCP 3. Model will be able to pull all designs off the screens 4. Basically tons of free Figma designs
0:35
0xSero's profile picture

If you're a frontend dev let me make your life easier: 1. Pay for mobbin. 2. Setup mobbin MCP 3. Model will be able to pull all designs off the screens 4. Basically tons of free Figma designs

0xSero

73,323 views • 2 months ago

Holy moly, MiniMax-M2.7 is amazing, watch till the end.
3:00
0xSero's profile picture

Holy moly, MiniMax-M2.7 is amazing, watch till the end.

0xSero

110,349 views • 4 months ago

GLM-5.1-478B-NVFP4 Running on: - 4x RTX Pro 6000 - Sglang - 370,000 max tokens (1.75x full context) - p10 27.7 | p90 45.6 tok/s decode (gen) - 1340 tok/s prefill I could get 2x decode if I limit to 64k context (100 tok/s) In this video it operates Figma (:
1:00
0xSero's profile picture

GLM-5.1-478B-NVFP4 Running on: - 4x RTX Pro 6000 - Sglang - 370,000 max tokens (1.75x full context) - p10 27.7 | p90 45.6 tok/s decode (gen) - 1340 tok/s prefill I could get 2x decode if I limit to 64k context (100 tok/s) In this video it operates Figma (:

0xSero

74,772 views • 3 months ago

GLM-5.2 running under my desk, modifying GGUFs to enable MTP on the Spark. What a world we live in, where you can have a megamind running off electrons going really fast.
0:27
0xSero's profile picture

GLM-5.2 running under my desk, modifying GGUFs to enable MTP on the Spark. What a world we live in, where you can have a megamind running off electrons going really fast.

0xSero

23,422 views • 24 days ago

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
0xSero's profile picture

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

87,959 views • 3 months ago

MiniMax-M3 running locally 100+ tok/s Good questions not often that models ask good questions.
1:23
0xSero's profile picture

MiniMax-M3 running locally 100+ tok/s Good questions not often that models ask good questions.

0xSero

32,537 views • 1 month ago

Finally, full precision MiniMax-M2.7 running at home. 100 tokens/s decode 5050 tokens/s prefill
0:36
0xSero's profile picture

Finally, full precision MiniMax-M2.7 running at home. 100 tokens/s decode 5050 tokens/s prefill

0xSero

72,465 views • 3 months ago

OAI has to be prioritising low/no thinking GPT-5.5 inference, it's so fast. I think this is better than high thinking, so much less annoying, so much more token efficient.
1:52
0xSero's profile picture

OAI has to be prioritising low/no thinking GPT-5.5 inference, it's so fast. I think this is better than high thinking, so much less annoying, so much more token efficient.

0xSero

65,255 views • 2 months ago

Guess who got GLM-5.2 at home? You can't deny I'm elite at inference.
0:31
0xSero's profile picture

Guess who got GLM-5.2 at home? You can't deny I'm elite at inference.

0xSero

27,083 views • 1 month ago

Let me save you hours of testing frontends. If you're ever working on a front-end, instead of writing tests, and adding puppeteer slop to your repo 1. Get an llm to write you with whatever needs to be tested 2. Copy that, go to browser 3. Open localhost with your selected app 4. Use Claude Chrome Extension or Parchi 5. Send it the prompt 6. QA engineering, there you go. Use models results and pass it back to your coding agent to fix whatever is flagged.
0:42
0xSero's profile picture

Let me save you hours of testing frontends. If you're ever working on a front-end, instead of writing tests, and adding puppeteer slop to your repo 1. Get an llm to write you with whatever needs to be tested 2. Copy that, go to browser 3. Open localhost with your selected app 4. Use Claude Chrome Extension or Parchi 5. Send it the prompt 6. QA engineering, there you go. Use models results and pass it back to your coding agent to fix whatever is flagged.

0xSero

109,943 views • 5 months ago

I yapped about LLM Compression for 40 minutes, how much misinformation did i spread this time (,:
39:49
0xSero's profile picture

I yapped about LLM Compression for 40 minutes, how much misinformation did i spread this time (,:

0xSero

35,181 views • 1 month ago

I LOVE Deepseek-v4-flash, incredibly reliable and capable, logical. It's lacking in frontend but I have MiMo for that. I would recommend any company spending 100k+ a year on AI to purchase 8-10~ 6000s and have a few of the works to have them blind test these models for work.
1:13
0xSero's profile picture

I LOVE Deepseek-v4-flash, incredibly reliable and capable, logical. It's lacking in frontend but I have MiMo for that. I would recommend any company spending 100k+ a year on AI to purchase 8-10~ 6000s and have a few of the works to have them blind test these models for work.

0xSero

51,035 views • 2 months ago