Loading video...

Video Failed to Load

Go Home

GLM 5.2 in Amp. Zero data retention, US and West-based inference. It's a good model. Try it now: amp update amp plugins add --auto-update @amp/glm-52-mode amp --mode glm-5.2

beyang's profile picture

Beyang

12,360 subscribers

92,323 views • 2 days ago •via X (Twitter)

Science & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

(Z.ai) is now a model provider inside TRAE. You can BYOK and add GLM-4.6 and GLM-4.5 to TRAE IDE. GLM-4.5 supports up to 128K context and GLM-4.6 expands up to 200K context. Both deliver strong coding and reasoning performance on the benchmark and offers dual “thinking/fast” modes. Available now in the latest version.
0:10

(Z.ai) is now a model provider inside TRAE. You can BYOK and add GLM-4.6 and GLM-4.5 to TRAE IDE. GLM-4.5 supports up to 128K context and GLM-4.6 expands up to 200K context. Both deliver strong coding and reasoning performance on the benchmark and offers dual “thinking/fast” modes. Available now in the latest version.

TRAE

63,501 views • 8 months ago

What if you could create stunning AI videos with zero limits, zero invite codes, and zero cost? That's GlobalGPT right now. 🎉 GLM 5.1 & Gemini 3.5 Flash are live — powering comic IPs, ads, dance & more with Happy Horse & Seedance. 👇
0:15

What if you could create stunning AI videos with zero limits, zero invite codes, and zero cost? That's GlobalGPT right now. 🎉 GLM 5.1 & Gemini 3.5 Flash are live — powering comic IPs, ads, dance & more with Happy Horse & Seedance. 👇

COLAW

70,384 views • 24 days ago

GLM-4.7 is supported in TRAE! You can plug in GLM-4.7 via as a custom model provider and run it directly in your agentic workflows.
0:10

GLM-4.7 is supported in TRAE! You can plug in GLM-4.7 via as a custom model provider and run it directly in your agentic workflows.

TRAE

21,474 views • 6 months ago

This model is insane at design. I asked GLM 5.2 (left) and Opus 4.8 (right) to build me a landing page and you can't even tell the difference. GLM cost $0.06 while opus cost $0.49. More than 6x cheaper while being faster + more token efficient. Another win for open source AI.
0:11

This model is insane at design. I asked GLM 5.2 (left) and Opus 4.8 (right) to build me a landing page and you can't even tell the difference. GLM cost $0.06 while opus cost $0.49. More than 6x cheaper while being faster + more token efficient. Another win for open source AI.

Hassan

1,465,406 views • 4 days ago

I'm looking forward to the release of 2-bit quantization for GLM-5.2. I'll try to see how much throughput I can squeeze out of my machine.
0:11

I'm looking forward to the release of 2-bit quantization for GLM-5.2. I'll try to see how much throughput I can squeeze out of my machine.

Hikari∣LocalLLM⚡

18,545 views • 4 days ago

Here's a comparison of Amp Tab to another popular tab-edit implementation. After removing fields, Amp Tab (dark mode) tabs nicely through all follow-on edits. Cursor (light mode) suggests re-adding just-removed fields.
0:15

Here's a comparison of Amp Tab to another popular tab-edit implementation. After removing fields, Amp Tab (dark mode) tabs nicely through all follow-on edits. Cursor (light mode) suggests re-adding just-removed fields.

Beyang

11,150 views • 10 months ago

GLM-4.7, now live in Crush.
0:10

GLM-4.7, now live in Crush.

Charm

41,629 views • 6 months ago

i found a way to make UNCENSORED AI AGENT on a RTX 4090 GPU (!!!) with LOCAL 30B model weights this is GLM-4.7-Flash with abliteration, need 24GB VRAM, safety alignment surgically removed from the weights, the model has native tool calling, it actually executes bash, edits files, runs git (1) use ollama to pull weights of GLM > ollama pull huihui_ai/glm-4.7-flash-abliterated:q4_K (2) proxy it to any coding agent via ollama > ollama launch claude --model huihui_ai/glm-4.7-flash-abliterated:q4_K > ollama launch codex --model huihui_ai/glm-4.7-flash-abliterated:q4_K > ollama launch opencode --model huihui_ai/glm-4.7-flash-abliterated:q4_K (3) have fun
0:11

i found a way to make UNCENSORED AI AGENT on a RTX 4090 GPU (!!!) with LOCAL 30B model weights this is GLM-4.7-Flash with abliteration, need 24GB VRAM, safety alignment surgically removed from the weights, the model has native tool calling, it actually executes bash, edits files, runs git (1) use ollama to pull weights of GLM > ollama pull huihui_ai/glm-4.7-flash-abliterated:q4_K (2) proxy it to any coding agent via ollama > ollama launch claude --model huihui_ai/glm-4.7-flash-abliterated:q4_K > ollama launch codex --model huihui_ai/glm-4.7-flash-abliterated:q4_K > ollama launch opencode --model huihui_ai/glm-4.7-flash-abliterated:q4_K (3) have fun

chiefofautism

340,773 views • 4 months ago

GLM-5 is live on 0G Compute. 744B parameters. SOTA open-source. MIT license. Beats GPT-5.2 on BrowseComp and Terminal-Bench. Run the world's best open model on decentralized infrastructure. No cloud vendor. No data logging. No ToS surprises. Your prompts stay yours.
0:14

GLM-5 is live on 0G Compute. 744B parameters. SOTA open-source. MIT license. Beats GPT-5.2 on BrowseComp and Terminal-Bench. Run the world's best open model on decentralized infrastructure. No cloud vendor. No data logging. No ToS surprises. Your prompts stay yours.

0G Labs (Home of Infinite AI)

77,923 views • 4 months ago

🤗 GLM-4.7-Flash is now live on Hugging Face , powered by Novita. Try it yourself 👇
0:11

🤗 GLM-4.7-Flash is now live on Hugging Face , powered by Novita. Try it yourself 👇

Novita AI

29,991 views • 5 months ago

GLM 5.2 dynamic 1-bit GGUF one shot Flappy Bird with 0 syntax errors whilst being 86% smaller! I was very surprised since normally 1-bit quants get syntax errors & you have to say "Fix bugs". UD 1-bit retained 76.2% top-1% accuracy whilst being 86% smaller vs BF16!
0:15

GLM 5.2 dynamic 1-bit GGUF one shot Flappy Bird with 0 syntax errors whilst being 86% smaller! I was very surprised since normally 1-bit quants get syntax errors & you have to say "Fix bugs". UD 1-bit retained 76.2% top-1% accuracy whilst being 86% smaller vs BF16!

Daniel Han

48,875 views • 3 days ago

Cool: Hugging Face is now supported in opencode, select your favorite model from the Hub and it will consume your inference quota directly. I recommend starting with GLM-4.5 (great at coding + awesome at agentic tasks)
0:14

Cool: Hugging Face is now supported in opencode, select your favorite model from the Hub and it will consume your inference quota directly. I recommend starting with GLM-4.5 (great at coding + awesome at agentic tasks)

Victor M

50,554 views • 10 months ago

Whoa, GLM-5.2 is INSANE for UI/UX with the right prompting. Open models have finally closed the gap. You have to push it, but it's super creative. I just asked for a beautiful personal site; this was all the model's idea (multiple turns):
0:16

Whoa, GLM-5.2 is INSANE for UI/UX with the right prompting. Open models have finally closed the gap. You have to push it, but it's super creative. I just asked for a beautiful personal site; this was all the model's idea (multiple turns):

Anshu

153,992 views • 5 days ago

👑 New Game Mode 🪜 Trophy Road Rework 👥 New Legendary & Evolution AND MORE! Check out Clash Royale's latest update!
0:19

👑 New Game Mode 🪜 Trophy Road Rework 👥 New Legendary & Evolution AND MORE! Check out Clash Royale's latest update!

Clash Royale

1,434,316 views • 11 months ago

GLM 5.2 has just been released 🔥 Here it's already running with MLX on two Mac Studios (M3 Ultra). This is comparable to the latest closed models, with weights you can download, quantize, distill, fine-tune, run.
0:11

GLM 5.2 has just been released 🔥 Here it's already running with MLX on two Mac Studios (M3 Ultra). This is comparable to the latest closed models, with weights you can download, quantize, distill, fine-tune, run.

Pedro Cuenca

81,984 views • 5 days ago

GLM-4.7 Flash by Z.ai running on M3 Ultra using MLX! 4bit at 81 toks/s 🔥 8bit at 64 toks/s 🔥 (video below) Model converted from transformers to MLX on the fly with Codex + GPT-5.2 HIgh!
0:19

GLM-4.7 Flash by Z.ai running on M3 Ultra using MLX! 4bit at 81 toks/s 🔥 8bit at 64 toks/s 🔥 (video below) Model converted from transformers to MLX on the fly with Codex + GPT-5.2 HIgh!

Ivan Fioravanti ᯅ

75,425 views • 5 months ago

a new competitive mode & Brawl Stars is in Subway Surfers now #subwaysurfers #brawlstars
0:12

a new competitive mode & Brawl Stars is in Subway Surfers now #subwaysurfers #brawlstars

Subway Surfers

18,969 views • 9 months ago

%@#&((&%_&>🫪 IG Story Update: emiamily ꒰ #emiamily เอหมี ꒱
0:20

%@#&((&%_&>🫪 IG Story Update: emiamily ꒰ #emiamily เอหมี ꒱

EMI THASORN OFFICIAL

20,805 views • 2 months ago

🚀 It's *finally* here. - Input pinned to top (Reverse Mode) - Input starting at top (Classic Mode) Update Warp and try it out for yourself!
0:15

🚀 It's *finally* here. - Input pinned to top (Reverse Mode) - Input starting at top (Classic Mode) Update Warp and try it out for yourself!

Warp

122,012 views • 3 years ago

life update 🥰 Q&A video out now
0:18

life update 🥰 Q&A video out now

Gina Wap

465,538 views • 9 months ago