正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

MLX + OpenCode + Qwen3.5-122B-A10B-4bit on M3 Ultra created a great snake game! Work zero-shot. Video clearly in super fast mode during generation. I generated the prompt using Grok 4.20, it's in the article.

Ivan Fioravanti ᯅ

22,131 subscribers

74,659 次观看 • 4 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

MiniMax M2.1 in 4-bit cruises on an M3 Ultra with mlx-lm. Generated a space invaders game using 5098 tokens at 47.2 tok/sec:

MiniMax M2.1 in 4-bit cruises on an M3 Ultra with mlx-lm. Generated a space invaders game using 5098 tokens at 47.2 tok/sec:

Awni Hannun

93,826 次观看 • 6 个月前

Step-3.5-Flash in action on MLX with OpenCode on a single (distributed testing in progress!) M3 Ultra to create a snake game! 🔥 6bit quantization. Perfect tool calling. Fast & powerful coding model! Recommended Inference Settings: Temperature: 1.0 Top-p: 0.95 Top-k: 40 🧵

Step-3.5-Flash in action on MLX with OpenCode on a single (distributed testing in progress!) M3 Ultra to create a snake game! 🔥 6bit quantization. Perfect tool calling. Fast & powerful coding model! Recommended Inference Settings: Temperature: 1.0 Top-p: 0.95 Top-k: 40 🧵

Ivan Fioravanti ᯅ

17,158 次观看 • 5 个月前

Qwen3.5 runs quite well in mlx-lm. Awesome that we have a frontier-level hybrid model. The context gets longer but the inference speed and memory use barely change. Here's the Q4 generating a space invaders game on an M3 Ultra. Generated 4,120 tokens at 37.6 tok/s.

Qwen3.5 runs quite well in mlx-lm. Awesome that we have a frontier-level hybrid model. The context gets longer but the inference speed and memory use barely change. Here's the Q4 generating a space invaders game on an M3 Ultra. Generated 4,120 tokens at 37.6 tok/s.

Awni Hannun

48,673 次观看 • 5 个月前

Qwen 3.5 397B prompt processing on M3 Ultra (with MLX distributed + JACCL) - 3.4× speedup on 4 chips - scaling improves as context increases Really fun to use with opencode; generated a playable Asteroids clone in ~4 minutes (real time, including me playing it a bit).

Qwen 3.5 397B prompt processing on M3 Ultra (with MLX distributed + JACCL) - 3.4× speedup on 4 chips - scaling improves as context increases Really fun to use with opencode; generated a playable Asteroids clone in ~4 minutes (real time, including me playing it a bit).

Angelos Katharopoulos

23,552 次观看 • 4 个月前

GLM-5 runs with mlx-lm on a single 512GB M3 Ultra in Q4. It's quite good in my initial testing and pretty fast as well. It generated a highly functional space invaders game using 7.1k tokens at 15.4 tok/s and 419GB memory. Thanks to Gökdeniz Gülmez and Tarjei Mandt for the port.

GLM-5 runs with mlx-lm on a single 512GB M3 Ultra in Q4. It's quite good in my initial testing and pretty fast as well. It generated a highly functional space invaders game using 7.1k tokens at 15.4 tok/s and 419GB memory. Thanks to Gökdeniz Gülmez and Tarjei Mandt for the port.

Awni Hannun

60,599 次观看 • 5 个月前

🔥 DeepSeek R1 671B Q4 - M3 Ultra 512GB with MLX🔥 - 18.43 tokens/sec - Generates a p5js zero-shot, tested at video's end 😱 - Video in real-time, no acceleration! - First test, and I'm blown away! Prompt: "Create an amazing animation using p5js"

🔥 DeepSeek R1 671B Q4 - M3 Ultra 512GB with MLX🔥 - 18.43 tokens/sec - Generates a p5js zero-shot, tested at video's end 😱 - Video in real-time, no acceleration! - First test, and I'm blown away! Prompt: "Create an amazing animation using p5js"

Ivan Fioravanti ᯅ

46,493 次观看 • 1 年前

Kimi K2.5 1T runs on 2 M3 Ultras with mlx-lm in it's native precision. It's actually quite usable. Here it's making a space invaders game. Generated 3856 tokens at 21.9 tok/sec using 350GB per machine. Thanks to Tarjei Mandt for the port.

Kimi K2.5 1T runs on 2 M3 Ultras with mlx-lm in it's native precision. It's actually quite usable. Here it's making a space invaders game. Generated 3856 tokens at 21.9 tok/sec using 350GB per machine. Thanks to Tarjei Mandt for the port.

Awni Hannun

241,472 次观看 • 5 个月前

A long time coming but new mlx-lm is here with better batching support in the server and Gemma 4. pip install -U mlx-lm Here is a video where a single M3 Ultra serves 5 opencode sessions with Gemma 4 26B that process ~130k tokens in ~1.5 minutes.

A long time coming but new mlx-lm is here with better batching support in the server and Gemma 4. pip install -U mlx-lm Here is a video where a single M3 Ultra serves 5 opencode sessions with Gemma 4 26B that process ~130k tokens in ~1.5 minutes.

Angelos Katharopoulos

66,202 次观看 • 3 个月前

Just for fun, here's what 32 simultaneous long-context generations with Qwen3 Next 80B looks like on an M3 Ultra. Using the new batch generation in mlx-lm. Context size for each is about 5k tokens:

Just for fun, here's what 32 simultaneous long-context generations with Qwen3 Next 80B looks like on an M3 Ultra. Using the new batch generation in mlx-lm. Context size for each is about 5k tokens:

Awni Hannun

50,272 次观看 • 9 个月前

I spent 5 hours today making OpenClaw even better at Motion Graphics I created the video below in 2 prompts with no asset uploads. It scraped or generated everything from a text prompt. I've added: - better brand scraping - image generation - video generation - music generation and scraping - better transitions on first prompt - basically zero errors - Always outputs a link to the editor you see below so I can open it from any device... (I can create and edit from telegram) Still work to do I will make a video this weekend and release the skill. It's the best remotion skill that exists imo.

Riley Brown

120,252 次观看 • 4 个月前

A 30-second scene created from an image (created by Grok). I animated it for 10 seconds (without a prompt) and then clicked on "Extend Video" twice. Grok decided on the animation, and I think he did a great job. Grok Imagine

A 30-second scene created from an image (created by Grok). I animated it for 10 seconds (without a prompt) and then clicked on "Extend Video" twice. Grok decided on the animation, and I think he did a great job. Grok Imagine

Déborah

13,083 次观看 • 3 个月前

Grok 4.5 in Grok Build is insane for 3D game dev🤯 I ran a detailed prompt using the /goal feature and I created this in only two prompts. Took roughly an hour. The model rigged all the enemy humanoids and made a fleshed out map and AI logic.

Grok 4.5 in Grok Build is insane for 3D game dev🤯 I ran a detailed prompt using the /goal feature and I created this in only two prompts. Took roughly an hour. The model rigged all the enemy humanoids and made a fleshed out map and AI logic.

Jayden Davis

907,640 次观看 • 6 天前

I'm proud to present this video created with Grok. Here are the main steps in the making of this video: 1. I wrote a draft script by hand. 2. I reworked the script with Grok to eliminate inconsistencies and add technical details (what I have them say about the Apollo missions and the stones is accurate). 3. Grok broke it down into scenes. 4. I switched to Grok Imagine's Agent mode: transforming each scene into a prompt. 5. I animated each scene in Agent mode using video, as well as cropping and image selection. 6. I edited it. Here's the result; it's hard to call it AI. I look forward to reading your comments. Grok Imagine Elon Musk

I'm proud to present this video created with Grok. Here are the main steps in the making of this video: 1. I wrote a draft script by hand. 2. I reworked the script with Grok to eliminate inconsistencies and add technical details (what I have them say about the Apollo missions and the stones is accurate). 3. Grok broke it down into scenes. 4. I switched to Grok Imagine's Agent mode: transforming each scene into a prompt. 5. I animated each scene in Agent mode using video, as well as cropping and image selection. 6. I edited it. Here's the result; it's hard to call it AI. I look forward to reading your comments. Grok Imagine Elon Musk

Déborah

69,706 次观看 • 1 个月前

Made medieval battle cinematic using multiple tools. AI content isn't just about using tools. It's about how you chain them together. Tools used GPT image 2.0 : Image Generation Claude: storyboard structure + per-cut video prompts Kling+Grok: video generation CapCut: editing Prompt in the comments

Made medieval battle cinematic using multiple tools. AI content isn't just about using tools. It's about how you chain them together. Tools used GPT image 2.0 : Image Generation Claude: storyboard structure + per-cut video prompts Kling+Grok: video generation CapCut: editing Prompt in the comments

FATHELA ESQ

31,023 次观看 • 2 天前

Grok 4 coded this great 3D Ball runner game based on a few prompts. It's easy to play in the Grok window.

Grok 4 coded this great 3D Ball runner game based on a few prompts. It's easy to play in the Grok window.

Testlabor

3,030,705 次观看 • 11 个月前

GLM 4.6 runs quite fast on an M3 Ultra with mlx-lm even at higher precision. Pretty remarkable that it benchmarks competitive to the just-released Sonnet 4.5. Hope those benchmarks hold-up in day-to-day use. Here's a run using 5.5 bpw quantized model, generating 5.3k tokens at 17+ tok/sec using 244 GB. What prompts should I test?

GLM 4.6 runs quite fast on an M3 Ultra with mlx-lm even at higher precision. Pretty remarkable that it benchmarks competitive to the just-released Sonnet 4.5. Hope those benchmarks hold-up in day-to-day use. Here's a run using 5.5 bpw quantized model, generating 5.3k tokens at 17+ tok/sec using 244 GB. What prompts should I test?

Awni Hannun

68,539 次观看 • 9 个月前

OpenCode + GLM-4.7-Flash 8bit. llama-server vs mlx_lm.server. Using one M3 Ultra for each host. Same prompts, you can check duration for each step in the video. Amazing experience on both side! Local coding AI model are becoming reality! 🔥

OpenCode + GLM-4.7-Flash 8bit. llama-server vs mlx_lm.server. Using one M3 Ultra for each host. Same prompts, you can check duration for each step in the video. Amazing experience on both side! Local coding AI model are becoming reality! 🔥

Ivan Fioravanti ᯅ

47,093 次观看 • 5 个月前

Sci-fi "drama" pt2 with Grok Imagine 0.9, don't take it too seriously this was created v fast in Grok last night after a fun first generation, I made sure to keep everything in the Grok model including sounds which I reused here and there or extracted from other failed generations. It's just FUN! 🔊🔊

Sci-fi "drama" pt2 with Grok Imagine 0.9, don't take it too seriously this was created v fast in Grok last night after a fun first generation, I made sure to keep everything in the Grok model including sounds which I reused here and there or extracted from other failed generations. It's just FUN! 🔊🔊

Stevie Mac

8,829,240 次观看 • 9 个月前

Created a full-length Labor Day Sale ad for a pet store called 'Pawfect Picks' using a single prompt. Time: ~30 mins Cost: $20 (= 20 credits) on invideo's Generative Ultra plan Exact prompt in the tweet below 👇

Created a full-length Labor Day Sale ad for a pet store called 'Pawfect Picks' using a single prompt. Time: ~30 mins Cost: $20 (= 20 credits) on invideo's Generative Ultra plan Exact prompt in the tweet below 👇

Sanket Shah

117,358 次观看 • 10 个月前

Another example of video extension using the latest Grok Imagine update: I created an image in Grok Imagine. I animated it. Then I clicked on video extension: you can choose 6 seconds or 10 seconds, write an animation prompt, and select the starting image. This ensures perfect continuity of the scene: fluidity of the image and sound atmosphere (music and sound effects).

Another example of video extension using the latest Grok Imagine update: I created an image in Grok Imagine. I animated it. Then I clicked on video extension: you can choose 6 seconds or 10 seconds, write an animation prompt, and select the starting image. This ensures perfect continuity of the scene: fluidity of the image and sound atmosphere (music and sound effects).

Déborah

628,917 次观看 • 4 个月前