Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

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.

pcuenq's profile picture

Pedro Cuenca

7,432 subscribers

81,984 Aufrufe • vor 7 Tagen •via X (Twitter)

BildungNachrichten & PolitikWissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

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 Aufrufe • vor 5 Monaten

Running Kimi K2.5 on my desk. Runs at 24 tok/sec with 2 x 512GB M3 Ultra Mac Studios connected with Thunderbolt 5 (RDMA) using EXO Labs / MLX backend. Yes, it can run clawdbot.
0:18

Running Kimi K2.5 on my desk. Runs at 24 tok/sec with 2 x 512GB M3 Ultra Mac Studios connected with Thunderbolt 5 (RDMA) using EXO Labs / MLX backend. Yes, it can run clawdbot.

Alex Cheema

3,041,206 Aufrufe • vor 4 Monaten

Playing with Qwen3-TTS is and MLX-Audio locally on Mac Studio M3 Ultra 🔥 Amazing model by Qwen and great work by Prince Canuma bringing this magic to MLX! Tuning the voice with instructions feels like magic! Command and prompts to run it are in the video.
0:17

Playing with Qwen3-TTS is and MLX-Audio locally on Mac Studio M3 Ultra 🔥 Amazing model by Qwen and great work by Prince Canuma bringing this magic to MLX! Tuning the voice with instructions feels like magic! Command and prompts to run it are in the video.

Ivan Fioravanti ᯅ

35,720 Aufrufe • vor 5 Monaten

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

174,727 Aufrufe • vor 6 Tagen

MiniMax M2.5 casually responding at ~50 tok/s with MLX (M3 Ultra). The model was released one hour ago 🥳
0:14

MiniMax M2.5 casually responding at ~50 tok/s with MLX (M3 Ultra). The model was released one hour ago 🥳

Pedro Cuenca

170,493 Aufrufe • vor 4 Monaten

Running DeepSeek R1 on my desk Uses EXO Labs with Thunderbolt 5 interconnect (80Gbps) to run the full (671B, 8-bit) DeepSeek R1 distributed across 2 M3 Ultra 512GB Mac Studios (1TB total Unified Memory). Runs at 11 tok/sec. Theoretical max is ~20 tok/sec.
0:14

Running DeepSeek R1 on my desk Uses EXO Labs with Thunderbolt 5 interconnect (80Gbps) to run the full (671B, 8-bit) DeepSeek R1 distributed across 2 M3 Ultra 512GB Mac Studios (1TB total Unified Memory). Runs at 11 tok/sec. Theoretical max is ~20 tok/sec.

Alex Cheema

992,119 Aufrufe • vor 1 Jahr

LM Studio 0.3.4 ships with Apple MLX 🚢🍎 Run on-device LLMs super fast, 100% locally and offline on your Apple Silicon Mac! Includes: > run Llama 3.2 1B at ~250 tok/sec (!) on M3 > enforce structured JSON responses > use via chat UI, or from your own code > run multiple models simultaneously > download any model from Hugging Face Video at 1x speed.
0:19

LM Studio 0.3.4 ships with Apple MLX 🚢🍎 Run on-device LLMs super fast, 100% locally and offline on your Apple Silicon Mac! Includes: > run Llama 3.2 1B at ~250 tok/sec (!) on M3 > enforce structured JSON responses > use via chat UI, or from your own code > run multiple models simultaneously > download any model from Hugging Face Video at 1x speed.

LM Studio

171,577 Aufrufe • vor 1 Jahr

Sam 3 by Facebook now on MLX 🚀 Here is a realtime object tracking running on M3 Max 96GB.
0:16

Sam 3 by Facebook now on MLX 🚀 Here is a realtime object tracking running on M3 Max 96GB.

Prince Canuma

180,245 Aufrufe • vor 2 Monaten

Qwen2.5-VL now on MLX 🚀 You can now run inference or train it locally on your Mac using MLX. > pip install -U mlx-vlm Note: Video support is coming shortly :) Model cards 👇🏾
0:18

Qwen2.5-VL now on MLX 🚀 You can now run inference or train it locally on your Mac using MLX. > pip install -U mlx-vlm Note: Video support is coming shortly :) Model cards 👇🏾

Prince Canuma

29,952 Aufrufe • vor 1 Jahr

Billy's stupid dance is just to make you notice that a new #manga has just been released with him. 39 pages. An adult woman with big curves will show this boy something new😉 You can download the full manga on my Unifans page. #shota #ショタ #aivideo #AIイラスト
0:14

Billy's stupid dance is just to make you notice that a new #manga has just been released with him. 39 pages. An adult woman with big curves will show this boy something new😉 You can download the full manga on my Unifans page. #shota #ショタ #aivideo #AIイラスト

Haru

11,854 Aufrufe • vor 1 Jahr

Qwen 3 0.6B is Ultra powerful if fine-tuned! Here I got 83.5% on classification tasks! Only Gemini 2.5 Pro does better with 85%! Video is in real time on M3 Ultra!
0:19

Qwen 3 0.6B is Ultra powerful if fine-tuned! Here I got 83.5% on classification tasks! Only Gemini 2.5 Pro does better with 85%! Video is in real time on M3 Ultra!

Ivan Fioravanti ᯅ

143,105 Aufrufe • vor 1 Jahr

EXO 1.0 at Apple NeurIPS booth. 4 x 512GB M3 Ultra Mac Studios clustered all-to-all with RDMA over Thunderbolt 5. Runs DeepSeek v3.2 (8-bit) at 25 tok/sec with tensor parallelism.
0:15

EXO 1.0 at Apple NeurIPS booth. 4 x 512GB M3 Ultra Mac Studios clustered all-to-all with RDMA over Thunderbolt 5. Runs DeepSeek v3.2 (8-bit) at 25 tok/sec with tensor parallelism.

EXO Labs

185,728 Aufrufe • vor 6 Monaten

Qwen/Qwen3-30B-A3B is absolute game changer 🤯 ⬇️ Are you on a Mac? then use MLX weights - getting 100 tokens/sec here. It changes everything for real world use cases.
0:15

Qwen/Qwen3-30B-A3B is absolute game changer 🤯 ⬇️ Are you on a Mac? then use MLX weights - getting 100 tokens/sec here. It changes everything for real world use cases.

Victor M

142,543 Aufrufe • vor 1 Jahr

Mac Studio M2 Ultra is best Apple Silicon ever (so far!) 🔥75 t/s and 0 throttling 🔥 Even after 20 mins of uninterrupted token generation with Apple MLX and mlx-community/Meta-Llama-3.1-8B-Instruct-8bit model!
0:13

Mac Studio M2 Ultra is best Apple Silicon ever (so far!) 🔥75 t/s and 0 throttling 🔥 Even after 20 mins of uninterrupted token generation with Apple MLX and mlx-community/Meta-Llama-3.1-8B-Instruct-8bit model!

Ivan Fioravanti ᯅ

11,041 Aufrufe • vor 1 Jahr

i just tested to put GLM-5.2 on my rig. 753B parameter MoE. 2x RTX PRO 6000 Blackwells, Threadripper PRO 9995WX with 1TB DDR5. prefills at 64 tok/s. decode holds at 13-15. system RAM bandwidth is the bottleneck. running UD-Q4_K_XL 4-bit. 69.7% on Aider Polyglot, within two points of BF16. left the 5090 off. mismatched VRAM unbalances the split. this is what local AI looks like now. massive frontier models on a "desktop rig". how awesome is this? and this is the worst it'll ever be.
0:18

i just tested to put GLM-5.2 on my rig. 753B parameter MoE. 2x RTX PRO 6000 Blackwells, Threadripper PRO 9995WX with 1TB DDR5. prefills at 64 tok/s. decode holds at 13-15. system RAM bandwidth is the bottleneck. running UD-Q4_K_XL 4-bit. 69.7% on Aider Polyglot, within two points of BF16. left the 5090 off. mismatched VRAM unbalances the split. this is what local AI looks like now. massive frontier models on a "desktop rig". how awesome is this? and this is the worst it'll ever be.

Samuel Cardillo

42,696 Aufrufe • vor 1 Tag

🔥 DFlash x MLX is happening! Shoutout to Arya Manjaramkar for the early work on this. We're building on the momentum. Native MLX support, more models (Qwen3.5), up to 4x faster. Lossless! 👉
0:17

🔥 DFlash x MLX is happening! Shoutout to Arya Manjaramkar for the early work on this. We're building on the momentum. Native MLX support, more models (Qwen3.5), up to 4x faster. Lossless! 👉

Zhijian Liu

214,332 Aufrufe • vor 2 Monaten

Batching for vision models is now available in Beta with our latest MLX engine update 👾 The updated engine also brings major improvements to caching for faster inference overall. Turn on Developer Mode, choose the beta runtime channel, and select LM Studio MLX v1.8.1.
0:11

Batching for vision models is now available in Beta with our latest MLX engine update 👾 The updated engine also brings major improvements to caching for faster inference overall. Turn on Developer Mode, choose the beta runtime channel, and select LM Studio MLX v1.8.1.

LM Studio

46,015 Aufrufe • vor 1 Monat

Step1X-Edit (MIT licensed) can provide comparable performance against the closed-source models like GPT-4o and Gemini2 Flash 🔥 🔥 Explore the app on Hugging Face now!
0:16

Step1X-Edit (MIT licensed) can provide comparable performance against the closed-source models like GPT-4o and Gemini2 Flash 🔥 🔥 Explore the app on Hugging Face now!

Gradio

20,919 Aufrufe • vor 1 Jahr

Jan Desktop v0.7.7 is live 💛 This update brings native MLX support on macOS, a broader UX and UI refresh across the app, and better support for developer workflows. You can now upload files in Projects, use the local API server with both local and remote models, and work more smoothly with tools like Claude Code and other CLIs. Update your Jan or download the latest version at
0:12

Jan Desktop v0.7.7 is live 💛 This update brings native MLX support on macOS, a broader UX and UI refresh across the app, and better support for developer workflows. You can now upload files in Projects, use the local API server with both local and remote models, and work more smoothly with tools like Claude Code and other CLIs. Update your Jan or download the latest version at

👋 Jan

28,378 Aufrufe • vor 4 Monaten

Qwen 3.5 9B. Running locally. With tool use. Already on your Mac.
0:19

Qwen 3.5 9B. Running locally. With tool use. Already on your Mac.

Osaurus

306,792 Aufrufe • vor 3 Monaten