Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

GLM 5.3 Flash on 2x RTX PRO 6000s

MiaAI_lab's profile picture

Mia

45,245 subscribers

49,494 Aufrufe • vor 1 Tag •via X (Twitter)

Wissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

38 Kommentare

Profilbild von OlympicDrinkingTeam
OlympicDrinkingTeamvor 1 Tag

@NVIDIAAI If I'm reading the new recipe right, there's nothing like spill? That was a game-changer for those of us who use multiple long-running chats...

Profilbild von Mia
Miavor 1 Tag

@NVIDIAAI This is the new recipe yes.

Profilbild von Colt Feltes
Colt Feltesvor 1 Tag

@NVIDIAAI Okay, but slow the video down 😆

Profilbild von Mia
Miavor 1 Tag

@NVIDIAAI hahaha yeah need to do 0.5x

Profilbild von Aaron Kendziorek
Aaron Kendziorekvor 1 Tag

@NVIDIAAI

Profilbild von Terp
Terpvor 1 Tag

@NVIDIAAI Zoomy, zoomy

Profilbild von Runner
Runnervor 1 Tag

@NVIDIAAI @davekennedy end game

Profilbild von Chad Hurley is Volatile Markets
Chad Hurley is Volatile Marketsvor 1 Tag

@TechMDAI @NVIDIAAI @MiaAI_lab how fast would she be if you had (4)? @NVIDIAAI

Profilbild von Petr
Petrvor 1 Tag

@TechMDAI @NVIDIAAI Need this xd

Profilbild von Miran
Miranvor 1 Tag

@NVIDIAAI You don’t need frontier models at this speed

Profilbild von Anders
Andersvor 22 Stunden

@TechMDAI @NVIDIAAI That’s a serious stack. What throughput and quality are you achieving?

Profilbild von Knowix
Knowixvor 1 Tag

@NVIDIAAI legal models are getting really capable of recent , love the speed and direction at which they move in

Profilbild von Blockzilla · Electros
Blockzilla · Electrosvor 1 Tag

@NVIDIAAI dam thats fast

Profilbild von HealthRanger
HealthRangervor 1 Tag

@NVIDIAAI That's a recipe I'd like to see!

Profilbild von Runner
Runnervor 1 Tag

@NVIDIAAI Going to fire up a 0.8B on a 3060 so I can feel something

Profilbild von Eric
Ericvor 1 Tag

@NVIDIAAI 👀

Profilbild von Random Libertarian Tech Lead
Random Libertarian Tech Leadvor 1 Tag

@NVIDIAAI I think you're seeing why modern agentic UIs don't generally render token-by-token anymore lol.

Profilbild von GoldenEars
GoldenEarsvor 23 Stunden

@NVIDIAAI 🥲 My hope is that the project I'm building with "frontier" models provides me with the financial freedom to be more like Mia. Very cool stuff!

Profilbild von Autodiag.
Autodiag.vor 22 Stunden

@NVIDIAAI If only I had 50k to dump on a computer lol.

Profilbild von LordOfTheYaml
LordOfTheYamlvor 23 Stunden

@NVIDIAAI Crazy 😳

Profilbild von Rob L
Rob Lvor 1 Tag

@NVIDIAAI How many simultaneous streams it supports at 1M context window?

Profilbild von +e/acc
+e/accvor 23 Stunden

@NVIDIAAI ok how ?

Profilbild von Peter Morris
Peter Morrisvor 1 Tag

@NVIDIAAI That's so fast! How does it compare to 2xGB10 for speed and intelligence?

Profilbild von ClassicMain
ClassicMainvor 1 Tag

@NVIDIAAI Wanna see how this looks in @OpenWebUI with open terminal

Profilbild von Rambone
Rambonevor 1 Tag

@NVIDIAAI That's crisp. One can dream

Profilbild von Ryan Wright
Ryan Wrightvor 21 Stunden

@NVIDIAAI hyperspeed

Profilbild von Haydon Ryan 🇦🇺🇺🇸
Haydon Ryan 🇦🇺🇺🇸vor 1 Tag

@NVIDIAAI Side by sides with dsv4f 0731 would be awesome... I think i need to try this GLM

Profilbild von S-Treffi
S-Treffivor 1 Tag

@NVIDIAAI Wow! Wtf?! That's crazy!

Profilbild von J'son
J'sonvor 1 Tag

@NVIDIAAI That's awesome. I saw you said you use hermes as well. Is yours dumb too? 😂 If not, would like to know your setup.

Profilbild von David Rojas
David Rojasvor 23 Stunden

@NVIDIAAI Dang. That’s amazing!

Profilbild von Russell
Russellvor 23 Stunden

@NVIDIAAI good stuff. Now show them how you can get 8+ concurrent connections with multimillion deep KV caches with minimal impact to TPS. it's in 1.2.2 of TensorFold now.

Profilbild von Sweet Theta
Sweet Thetavor 1 Tag

@NVIDIAAI What is this UI / platform ?

Profilbild von Mia
Miavor 1 Tag

@NVIDIAAI my harness, unreleased yet

Profilbild von Radic Davydov
Radic Davydovvor 22 Stunden

@NVIDIAAI What's the actual tok/s? The video doesn't give any useful info.

Profilbild von Mike Gannotti 🔳
Mike Gannotti 🔳vor 1 Tag

@NVIDIAAI 🔥🔥🔥🔥

Profilbild von rduffy
rduffyvor 22 Stunden

@NVIDIAAI Sexy

Profilbild von Translating Ohio
Translating Ohiovor 1 Tag

@NVIDIAAI Damn... Are you working on any single 6000 recipes?

Profilbild von Yume_X
Yume_Xvor 22 Stunden

@TechMDAI @NVIDIAAI Crazy! 🔥🔥

Ähnliche Videos

How prose looks like in Hermes agent using GLM 5.3 Flash EXL3 on 2x DGX Sparks
0:30

How prose looks like in Hermes agent using GLM 5.3 Flash EXL3 on 2x DGX Sparks

Mia

10,574 Aufrufe • vor 2 Monaten

GLM 5.3 Flash on 2x DGX Sparks Look at the tok/s at the top :) This is prose. Releasing soon
0:23

GLM 5.3 Flash on 2x DGX Sparks Look at the tok/s at the top :) This is prose. Releasing soon

Mia

16,605 Aufrufe • vor 1 Monat

4 AI models trying to draw their self-portraits. GLM-5.3-Flash, GLM-5.3, Kimi K3, and Claude Opus 5. GLM-5.3-Flash came out looking the most handsome 🤓
0:50

4 AI models trying to draw their self-portraits. GLM-5.3-Flash, GLM-5.3, Kimi K3, and Claude Opus 5. GLM-5.3-Flash came out looking the most handsome 🤓

TypingMind

77,196 Aufrufe • vor 2 Monaten

GLM 5.3 Flash EXL3 running on 3x DGX Sparks.
0:27

GLM 5.3 Flash EXL3 running on 3x DGX Sparks.

Mia

12,535 Aufrufe • vor 1 Monat

- GLM 5.3 Flash EXL3 - 2x DGX Sparks - TensorFold - 4 concurrent prose streams Pay attention to tok/s and TTFT on each stream. Buttery smooth experience!
0:37

- GLM 5.3 Flash EXL3 - 2x DGX Sparks - TensorFold - 4 concurrent prose streams Pay attention to tok/s and TTFT on each stream. Buttery smooth experience!

Mia

32,293 Aufrufe • vor 1 Monat

Which flash model wins? DeepSeek v4.1 flash, Qwen 3.8 flash, or GLM 5.3 flash 🤯
0:41

Which flash model wins? DeepSeek v4.1 flash, Qwen 3.8 flash, or GLM 5.3 flash 🤯

GMI Cloud

15,052 Aufrufe • vor 1 Monat

Ran FlappyBench on DeepSeek V4.1-Flash, GLM 5.3, and Kimi K3 with the same /design prompt. 🔹 DSV4.1-Flash: 9/10 · $0.0089 one-shot with the lowest cost 🔹 GLM-5.3: 9.5/10 · $0.0184 · nailed the UI but cost 2x more 🔹 Kimi K3: 8/10 · $0.0740 · hard-coded gameplay and 8x more
0:25

Ran FlappyBench on DeepSeek V4.1-Flash, GLM 5.3, and Kimi K3 with the same /design prompt. 🔹 DSV4.1-Flash: 9/10 · $0.0089 one-shot with the lowest cost 🔹 GLM-5.3: 9.5/10 · $0.0184 · nailed the UI but cost 2x more 🔹 Kimi K3: 8/10 · $0.0740 · hard-coded gameplay and 8x more

Command Code

20,527 Aufrufe • vor 1 Monat

GLM 5.3 Flash running locally makes a Minecraft black hole mod We ran GLM 5.3 Flash Q4 locally on a rented 4x RTX PRO 6000 box and asked it to make a lightning gun mod for the real game using the Fabric API Output: -7.6M tokens -Time: ~9 hours -Decode: ~96 tok/s The mod adds a black hole rifle, when shot it spawns a black hole that pulls in blocks, with light rings that shrink all the way into the singularity, then collapses into an explosion crater that wipes out several chunks Run GLM 5.3 Flash locally in
0:22

GLM 5.3 Flash running locally makes a Minecraft black hole mod We ran GLM 5.3 Flash Q4 locally on a rented 4x RTX PRO 6000 box and asked it to make a lightning gun mod for the real game using the Fabric API Output: -7.6M tokens -Time: ~9 hours -Decode: ~96 tok/s The mod adds a black hole rifle, when shot it spawns a black hole that pulls in blocks, with light rings that shrink all the way into the singularity, then collapses into an explosion crater that wipes out several chunks Run GLM 5.3 Flash locally in

atomic.chat

32,515 Aufrufe • vor 2 Monaten

GLM 5.3 free on Kira AI, 100M tokens + 50M check-in 😳 GLM 5.3 + Flash + Qwen 3.8 Flash free. 1M context, no card. → → sign up → grab key → plug in Third-party proxy, don't send secrets. Go grab it.
0:27

GLM 5.3 free on Kira AI, 100M tokens + 50M check-in 😳 GLM 5.3 + Flash + Qwen 3.8 Flash free. 1M context, no card. → → sign up → grab key → plug in Third-party proxy, don't send secrets. Go grab it.

Punch AI

17,124 Aufrufe • vor 1 Monat

GLM 5.3 Flash vs DeepSeek V4.1 Flash 1017 Can't believe we're abusing gummy bears to test models, but here we are! Both models were run locally. - GLM 5.3 Flash: my own EXL3 quant (link below) - DeepSeek V4.1 Flash 1017: official quant - Same harness.Both on Max effort. Who won?
0:33

GLM 5.3 Flash vs DeepSeek V4.1 Flash 1017 Can't believe we're abusing gummy bears to test models, but here we are! Both models were run locally. - GLM 5.3 Flash: my own EXL3 quant (link below) - DeepSeek V4.1 Flash 1017: official quant - Same harness.Both on Max effort. Who won?

Mia

32,512 Aufrufe • vor 18 Tagen

Jumpgate - hyperspace jump DS4.1F-1017 vs GLM 5.3 Flash vs Fable 5.1 Who won imo: 🥇 Fable 5.1 🥈 DeepSeek V4.1 Flash 1017 🥉 GLM 5.3 Flash You can run these by yourself here: Prompt below.
0:24

Jumpgate - hyperspace jump DS4.1F-1017 vs GLM 5.3 Flash vs Fable 5.1 Who won imo: 🥇 Fable 5.1 🥈 DeepSeek V4.1 Flash 1017 🥉 GLM 5.3 Flash You can run these by yourself here: Prompt below.

Mia

13,071 Aufrufe • vor 16 Tagen

DeepSeek V4.1 Flash vs MiMo V2.6 Flash vs GLM 5.3 Flash vs LongCat 2.5 Preview All models 100% free on OpenCode Which one is the best?
0:30

DeepSeek V4.1 Flash vs MiMo V2.6 Flash vs GLM 5.3 Flash vs LongCat 2.5 Preview All models 100% free on OpenCode Which one is the best?

Rubens Soto | AI & SaaS

62,875 Aufrufe • vor 20 Tagen

$25 free credits on River AI right now 😳 DeepSeek V4.1 Flash + GLM-5.3 Flash at 20% cheaper than official rates. → Go grab it.
0:27

$25 free credits on River AI right now 😳 DeepSeek V4.1 Flash + GLM-5.3 Flash at 20% cheaper than official rates. → Go grab it.

Punch AI

13,434 Aufrufe • vor 24 Tagen

We gave GLM-5.3-Flash a Blender scene and 12 hours later it built this.
0:28

We gave GLM-5.3-Flash a Blender scene and 12 hours later it built this.

Lou

201,408 Aufrufe • vor 2 Monaten

GLM 5.3 Flash vs Hybrid (GLM 5.3 Flash + Jev) on a turn-based strategy game (Halite 2) The hybrid approach is 13x faster, 56% of the pure GLM 5.3 Flash API cost, and gains a slight edge in performance. In the hybrid approach: -GLM 5.3 Flash handles strategic judgment of which planets matter, who expands, who fights, when to re-plan. -Jev handles the ship-by-ship execution. GLM 5.3 Flash alone defeats Jev alone 82% of the time. This is obviously just a single example and some of the first things I've tried to make use of Jev as an augmentation to an LLM. Could potentially make even more gains in cost, speed, and performance, but using what I've figured out here, I am compelled to try some ideas with robotics next.
0:24

GLM 5.3 Flash vs Hybrid (GLM 5.3 Flash + Jev) on a turn-based strategy game (Halite 2) The hybrid approach is 13x faster, 56% of the pure GLM 5.3 Flash API cost, and gains a slight edge in performance. In the hybrid approach: -GLM 5.3 Flash handles strategic judgment of which planets matter, who expands, who fights, when to re-plan. -Jev handles the ship-by-ship execution. GLM 5.3 Flash alone defeats Jev alone 82% of the time. This is obviously just a single example and some of the first things I've tried to make use of Jev as an augmentation to an LLM. Could potentially make even more gains in cost, speed, and performance, but using what I've figured out here, I am compelled to try some ideas with robotics next.

Harrison Kinsley

54,330 Aufrufe • vor 1 Monat

Build & Train a GLM-5.3-Flash Model From Scratch I built a 25.7M-parameter educational model inspired by GLM-5.3-Flash, then tested its architecture, pretraining, and executable-reward reinforcement learning end to end. Repository: YouTube: Become AI researcher in 90 days:
44:05

Build & Train a GLM-5.3-Flash Model From Scratch I built a 25.7M-parameter educational model inspired by GLM-5.3-Flash, then tested its architecture, pretraining, and executable-reward reinforcement learning end to end. Repository: YouTube: Become AI researcher in 90 days:

Vuk Rosić 武克

14,590 Aufrufe • vor 2 Monaten

DeepSeek v4.1 Flash vs GLM 5.3 Flash I asked both models to recreate the Psychonauts 2 and Metroid Prime game menus as closely as possible to the originals. Attached are full-sized videos from both models for both games. All were done in a single shot, both at Max thinking, same harness. Tokens used: DeepSeek v4.1 Flash - Psychonauts 2: 412k - Metroid Prime: 466k GLM 5.3 Flash - Psychonauts 2: 134k - Metroid Prime: 111k That's between 3-4x MORE used by DS4.1F. Who do you think won? IMO GLM 5.3 Flash won by FAR on both.
0:20

DeepSeek v4.1 Flash vs GLM 5.3 Flash I asked both models to recreate the Psychonauts 2 and Metroid Prime game menus as closely as possible to the originals. Attached are full-sized videos from both models for both games. All were done in a single shot, both at Max thinking, same harness. Tokens used: DeepSeek v4.1 Flash - Psychonauts 2: 412k - Metroid Prime: 466k GLM 5.3 Flash - Psychonauts 2: 134k - Metroid Prime: 111k That's between 3-4x MORE used by DS4.1F. Who do you think won? IMO GLM 5.3 Flash won by FAR on both.

Mia

24,127 Aufrufe • vor 1 Monat

Ox Alpha is actually GLM-5.3-Flash, and it’s one of my favorite models ever released.
43:13

Ox Alpha is actually GLM-5.3-Flash, and it’s one of my favorite models ever released.

Theo - t3.gg

138,782 Aufrufe • vor 2 Monaten

NVIDIA is giving away 9 frontier AI models for free 🤯 • DeepSeek V4.1 Flash • Kimi K3 + K2.6 • GLM 5.3 + GLM 5.3 Flash • Nemotron 3 Ultra 550B • Nemotron 3 Super 120B • Nemotron 3.5 Lightning • Nemotron 3 Nano Omni No card, 40 req/min. Base URL:
0:20

NVIDIA is giving away 9 frontier AI models for free 🤯 • DeepSeek V4.1 Flash • Kimi K3 + K2.6 • GLM 5.3 + GLM 5.3 Flash • Nemotron 3 Ultra 550B • Nemotron 3 Super 120B • Nemotron 3.5 Lightning • Nemotron 3 Nano Omni No card, 40 req/min. Base URL:

Punch AI

17,655 Aufrufe • vor 1 Monat

GLM-5.3-Flash streaming at 32 tok/s on a single Spark via Tensorfold ⚡️ i will share the recipe later today
0:30

GLM-5.3-Flash streaming at 32 tok/s on a single Spark via Tensorfold ⚡️ i will share the recipe later today

filipe

15,230 Aufrufe • vor 1 Monat