Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Compared MiniMax M3 against three other frontier open-source models: DeepSeek V4, Qwen 3.7 Max, and MiMo 2.5 Pro MiniMax M3 crashed others on: 1. collision physics 2. 3D pinball generation It was the only model that produced a result for the 3D pinball test For human motion rendering and...

gmi_cloud's profile picture

GMI Cloud

5,096 subscribers

50,984 Aufrufe • vor 20 Tagen •via X (Twitter)

GamingBildungWissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

MiniMax M3 is now available on AI/ML API! To test it, we asked several leading models to oneshot Doodle Jump from the scratch. The results ended up looking far closer than the price tags. MiniMax M3: $0.05 Qwen 3.7 Max: $0.08 DeepSeek V4 Pro: $0.10 GPT-5.5: $0.42 Curious which one you'd pick in a blind comparison. We also offer it 50% off for a limited time. Find docs, guides for setting it up & prompt below
0:34

MiniMax M3 is now available on AI/ML API! To test it, we asked several leading models to oneshot Doodle Jump from the scratch. The results ended up looking far closer than the price tags. MiniMax M3: $0.05 Qwen 3.7 Max: $0.08 DeepSeek V4 Pro: $0.10 GPT-5.5: $0.42 Curious which one you'd pick in a blind comparison. We also offer it 50% off for a limited time. Find docs, guides for setting it up & prompt below

AI/ML API

535,499 Aufrufe • vor 20 Tagen

Qwen 3.7 Max is the best and fastest by far, 0 Shot 1 try Deepseek I'd say is 2nd, has some better obstacle avoidance. Impressive results all around but Qwen 3.7 Max has proper turret orientation and proper track marks.
0:42

Qwen 3.7 Max is the best and fastest by far, 0 Shot 1 try Deepseek I'd say is 2nd, has some better obstacle avoidance. Impressive results all around but Qwen 3.7 Max has proper turret orientation and proper track marks.

Loktar 🇺🇸

19,742 Aufrufe • vor 1 Monat

🚨UPDATE Qwen 3.7 MAX built me a 3D model of our universe 🤯 The Prompt: "Let’s build the entire observable universe from real astronomical data. Every documented star, constellation, nebula galaxy - exportable from your browser" Great work Tongyi Lab Qwen
0:26

🚨UPDATE Qwen 3.7 MAX built me a 3D model of our universe 🤯 The Prompt: "Let’s build the entire observable universe from real astronomical data. Every documented star, constellation, nebula galaxy - exportable from your browser" Great work Tongyi Lab Qwen

Eric ⚡️ Building...

13,213 Aufrufe • vor 27 Tagen

We just added a lot more models to our 100% free coding agent. Try the new MiniMax M3 or MiMo 2.5 Pro 🔥 It's free: npm i -g freebuff
0:23

We just added a lot more models to our 100% free coding agent. Try the new MiniMax M3 or MiMo 2.5 Pro 🔥 It's free: npm i -g freebuff

James Grugett

41,537 Aufrufe • vor 13 Tagen

Open-weight MiniMax M3 filled out a US customs form from a driver's license photo For this test we deployed MiniMax M3 Q4 using MLX-VLM on a Mac Studio M3 Ultra 512GB RAM. The model was tasked with reading a scanned document and an ID card photo, then completing a declaration form Output: 736 tokens · Input: 1,847 tokens · Time: ~31s The model analyzed both inputs, streamed its reasoning, and then called three tools: write_field for text fields, mark for Yes/No checkboxes, and sign for the signature and date. It extracted the required information, mapped it to the correct fields and completed the form without any manual input
0:20

Open-weight MiniMax M3 filled out a US customs form from a driver's license photo For this test we deployed MiniMax M3 Q4 using MLX-VLM on a Mac Studio M3 Ultra 512GB RAM. The model was tasked with reading a scanned document and an ID card photo, then completing a declaration form Output: 736 tokens · Input: 1,847 tokens · Time: ~31s The model analyzed both inputs, streamed its reasoning, and then called three tools: write_field for text fields, mark for Yes/No checkboxes, and sign for the signature and date. It extracted the required information, mapped it to the correct fields and completed the form without any manual input

atomic.chat

107,294 Aufrufe • vor 6 Tagen

I tested Gemma 4 12b on my Macbook Pro M5 Max with 128GB of unified memory. It runs VERY slow for a 12b parameter model. 44 tokens/second. The lava lamp that it produced was also terrible. I would stick to Qwen 3.6 27b or Qwen 3.6 35b. Google is still way behind, even with their local models.
1:36

I tested Gemma 4 12b on my Macbook Pro M5 Max with 128GB of unified memory. It runs VERY slow for a 12b parameter model. 44 tokens/second. The lava lamp that it produced was also terrible. I would stick to Qwen 3.6 27b or Qwen 3.6 35b. Google is still way behind, even with their local models.

BridgeMind

69,955 Aufrufe • vor 16 Tagen

Claude Opus 4.8 (Max) is definitely capable, but this test honestly surprised me. I gave it the same macOS-style web OS challenge and it spent 1 hour and 56 minutes, burned through 66k+ tokens, and still produced a result that was worse than what Qwen 3.7-Max generated. The biggest issue isn't quality, it's efficiency. Opus 4.8 can absolutely cook when given enough time, but the token usage and runtime are becoming harder and harder to justify when cheaper models are delivering comparable or even better results. Full Breakdown: The frontier is getting very competitive. 👀
1:14

Claude Opus 4.8 (Max) is definitely capable, but this test honestly surprised me. I gave it the same macOS-style web OS challenge and it spent 1 hour and 56 minutes, burned through 66k+ tokens, and still produced a result that was worse than what Qwen 3.7-Max generated. The biggest issue isn't quality, it's efficiency. Opus 4.8 can absolutely cook when given enough time, but the token usage and runtime are becoming harder and harder to justify when cheaper models are delivering comparable or even better results. Full Breakdown: The frontier is getting very competitive. 👀

WorldofAI

123,305 Aufrufe • vor 23 Tagen

DeepSeek beat out OpenAI then Alibaba released Qwen 2.5 Max
1:29

DeepSeek beat out OpenAI then Alibaba released Qwen 2.5 Max

Michael Burry Stock Tracker ♟

18,449 Aufrufe • vor 1 Jahr

Run OpenClaw locally with ollama 🦙 – Open source models: MiniMax, Qwen, Kimi and more – One click install on macOS and Windows – Local & cloud Ollama models connected atomicbot.ai where llamas meet claws 🦞
0:24

Run OpenClaw locally with ollama 🦙 – Open source models: MiniMax, Qwen, Kimi and more – One click install on macOS and Windows – Local & cloud Ollama models connected atomicbot.ai where llamas meet claws 🦞

atomicbot.ai

58,619 Aufrufe • vor 2 Monaten

Big Models. Complex Projects. Running Local. Our 128GB agent computers are now regularly loading and running large models like Step 3.7 and Qwen 3.5. 122B for heavy reasoning and overnight work using Ryzen AI Max+ 395 processors.
1:16

Big Models. Complex Projects. Running Local. Our 128GB agent computers are now regularly loading and running large models like Step 3.7 and Qwen 3.5. 122B for heavy reasoning and overnight work using Ryzen AI Max+ 395 processors.

AMD Ryzen

32,511 Aufrufe • vor 6 Tagen

The MiniMax M2 model is mind-blowing! It's open-source. It outperforms Gemini 2.5, Claude 4.1, and Qwen3 across coding and tool-use benchmarks. Right now, it's one of the world's top 5 models in intelligence! And here is the best part: Claude is one of the best models you can use today, and MiniMax M2 costs only 8% of that! It's smaller, faster, and cheaper. Extremely efficient at using tokens. Minimax M2's biggest strength: High agentic capabilities. The model can plan and execute complex multi-tool workflows. It's reliable and very robust at executing long-horizon tool chains. In summary: • Low latency • Very cheap • Excels at agentic tasks • Open-source The model currently powers the MiniMax Agent and is available for a free global trial. You can access MiniMax M2's API here: To access the agent: And here is the MiniMax website: Thanks to the MiniMax team for showing me the ropes and partnering with me on this post.
6:01

The MiniMax M2 model is mind-blowing! It's open-source. It outperforms Gemini 2.5, Claude 4.1, and Qwen3 across coding and tool-use benchmarks. Right now, it's one of the world's top 5 models in intelligence! And here is the best part: Claude is one of the best models you can use today, and MiniMax M2 costs only 8% of that! It's smaller, faster, and cheaper. Extremely efficient at using tokens. Minimax M2's biggest strength: High agentic capabilities. The model can plan and execute complex multi-tool workflows. It's reliable and very robust at executing long-horizon tool chains. In summary: • Low latency • Very cheap • Excels at agentic tasks • Open-source The model currently powers the MiniMax Agent and is available for a free global trial. You can access MiniMax M2's API here: To access the agent: And here is the MiniMax website: Thanks to the MiniMax team for showing me the ropes and partnering with me on this post.

Santiago

91,142 Aufrufe • vor 7 Monaten

MiniMax M3 vs GLM-5.2 vs Kimi K2.7 in Lunar Lander contest! 🔥 Last test of the day before going back to learning & build phase with Local Models, Swift and Apple Core AI 💪 I took the opportunity to test the MiniMax Code app for macOS. Video below speeded up. Followed by Lunar Lander implementation from the various models. My ranking: 🥇 GLM 5.2 🥈 MiniMax M3 🥉 Kimi K2.7 Coding Prompt and final results in this gist:
0:42

MiniMax M3 vs GLM-5.2 vs Kimi K2.7 in Lunar Lander contest! 🔥 Last test of the day before going back to learning & build phase with Local Models, Swift and Apple Core AI 💪 I took the opportunity to test the MiniMax Code app for macOS. Video below speeded up. Followed by Lunar Lander implementation from the various models. My ranking: 🥇 GLM 5.2 🥈 MiniMax M3 🥉 Kimi K2.7 Coding Prompt and final results in this gist:

Ivan Fioravanti ᯅ

21,098 Aufrufe • vor 7 Tagen

✨Spotlight: Top 4 Code Arena open models Open models are moving fast, and this community is directly shaping how that progress shows up in real use. Your builds, votes, and experiments surface what frontier models can actually do in practice. To celebrate the momentum, we’re spotlighting the top open models in Code Arena (WebDev) 🧵👇 🔥 MiniMax (official) — MiniMax-M2.1 🤖 Z.ai — GLM-4.7 ✨ DeepSeek — Deepseek-v3.2-thinking 🚀 Xiaomi MiMo — Mimo-v2-flash (non-thinking) Let’s keep building in the open and raising the bar together 🚀
1:07

✨Spotlight: Top 4 Code Arena open models Open models are moving fast, and this community is directly shaping how that progress shows up in real use. Your builds, votes, and experiments surface what frontier models can actually do in practice. To celebrate the momentum, we’re spotlighting the top open models in Code Arena (WebDev) 🧵👇 🔥 MiniMax (official) — MiniMax-M2.1 🤖 Z.ai — GLM-4.7 ✨ DeepSeek — Deepseek-v3.2-thinking 🚀 Xiaomi MiMo — Mimo-v2-flash (non-thinking) Let’s keep building in the open and raising the bar together 🚀

Arena.ai

16,742 Aufrufe • vor 5 Monaten

MiniMax M3 turned a napkin sketch into a playable game We handed MiniMax M3 a hand-drawn draft of a Doodle Jump style platformer. It read the elements off the draft, wrote the logic, drew the interface and shipped it as one self-contained HTML game Input: 6,920 tokens Output: 9,933 tokens Cost: $0.028 MiniMax (official) drops M3 on Hugging Face next week
0:21

MiniMax M3 turned a napkin sketch into a playable game We handed MiniMax M3 a hand-drawn draft of a Doodle Jump style platformer. It read the elements off the draft, wrote the logic, drew the interface and shipped it as one self-contained HTML game Input: 6,920 tokens Output: 9,933 tokens Cost: $0.028 MiniMax (official) drops M3 on Hugging Face next week

atomic.chat

64,254 Aufrufe • vor 20 Tagen

Introducing the new MacBook Pro lineup and iMac with the most advanced chips ever built for a personal computer. Say hello to M3, M3 Pro, and M3 Max—the latest breakthroughs in Apple silicon! #AppleEvent
1:41

Introducing the new MacBook Pro lineup and iMac with the most advanced chips ever built for a personal computer. Say hello to M3, M3 Pro, and M3 Max—the latest breakthroughs in Apple silicon! #AppleEvent

Tim Cook

2,512,308 Aufrufe • vor 2 Jahren

Vibing With Deepseek V3.1 - it's fast, and it's a big step up for V3 - still very far away from Sonnet 3.7 for real world coding Both Deepseek and Gemini Pro 2.5 are on ChatLLM
0:23

Vibing With Deepseek V3.1 - it's fast, and it's a big step up for V3 - still very far away from Sonnet 3.7 for real world coding Both Deepseek and Gemini Pro 2.5 are on ChatLLM

Bindu Reddy

35,105 Aufrufe • vor 1 Jahr

The latest Qwen 3 VL by Qwen running on iPhone 17 Pro with MLX Qwen 3 VL brings upgraded visual understanding, recognition, and OCR capabilities without sacrificing text performance like previous models The 4B model here is close to Qwen 2.5 VL 72B in many benchmarks
0:21

The latest Qwen 3 VL by Qwen running on iPhone 17 Pro with MLX Qwen 3 VL brings upgraded visual understanding, recognition, and OCR capabilities without sacrificing text performance like previous models The 4B model here is close to Qwen 2.5 VL 72B in many benchmarks

Adrien Grondin

109,700 Aufrufe • vor 8 Monaten

Most AI models feel like assistants. MiniMax M3 felt like a teammate. I used Cursor + the MiniMax M3 API to build TweetGen — a tool that generates tweets instantly for any topic. What surprised me wasn’t just the speed, but how naturally M3 handled the whole workflow. It scaffolded the repo, wrote clean code, corrected itself, and kept context across iterations. I wasn’t nudging it line by line — it was committing changes like a real collaborator. Instead of “AI that helps you code,” it felt like “AI that codes with you.” That shift is huge.
1:04

Most AI models feel like assistants. MiniMax M3 felt like a teammate. I used Cursor + the MiniMax M3 API to build TweetGen — a tool that generates tweets instantly for any topic. What surprised me wasn’t just the speed, but how naturally M3 handled the whole workflow. It scaffolded the repo, wrote clean code, corrected itself, and kept context across iterations. I wasn’t nudging it line by line — it was committing changes like a real collaborator. Instead of “AI that helps you code,” it felt like “AI that codes with you.” That shift is huge.

Mr. Jason💡

12,304 Aufrufe • vor 3 Tagen

Running Minimax M2.1 (MiniMax (official)) with OpenCode (OpenCode) and mlx_lm.server. Works quite well on an M3 Ultra. Once the KV cache is warm the prompt processing is pretty quick. And token generation is very fast.
0:41

Running Minimax M2.1 (MiniMax (official)) with OpenCode (OpenCode) and mlx_lm.server. Works quite well on an M3 Ultra. Once the KV cache is warm the prompt processing is pretty quick. And token generation is very fast.

Awni Hannun

32,329 Aufrufe • vor 5 Monaten