Loading video...

Video Failed to Load

Go Home

Local model update! 🚨 The MiniMax (official) 2.7 model has been powering my homeschool OpenClaw🦞 for a week without any issue 💕 Sooo much cheaper than Anthropic options in general, but with my Mac Studio it’s running for the cost of electricity!

jessegenet's profile picture

Jesse Genet

58,347 subscribers

32,938 views • 4 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Boom, the game is changed GLM 5.1 running locally seems to actually work… Now I can run a lot of my OpenClaw🦞 workflows for the cost of electricity 🔌
2:03

Boom, the game is changed GLM 5.1 running locally seems to actually work… Now I can run a lot of my OpenClaw🦞 workflows for the cost of electricity 🔌

Jesse Genet

81,556 views • 4 months ago

pretty impressed that MiniMax (official) 2.7 can one-shot a linear clone in 10 mins at 95% cheaper than claude opus 4.6 not enough people know about this model. if you're just using whatever your timeline is hyping, you're probably overpaying for the same result
0:33

pretty impressed that MiniMax (official) 2.7 can one-shot a linear clone in 10 mins at 95% cheaper than claude opus 4.6 not enough people know about this model. if you're just using whatever your timeline is hyping, you're probably overpaying for the same result

Sherry Jiang is at ai engineer singapore

140,954 views • 5 months ago

“This could have been possible six months ago.” Peter Steinberger 🦞 on what actually enabled OpenClaw🦞's success: “The models have been good for a while. It wasn’t a sudden model breakthrough.” “It required a certain amount of madness... letting a model do whatever it wants on your computer.” “I experimented with this for months. Nothing bad happened.” “If you understand the technology, it’s a calculated risk.” “And the upside is so large that it’s worth it.”
1:59

“This could have been possible six months ago.” Peter Steinberger 🦞 on what actually enabled OpenClaw🦞's success: “The models have been good for a while. It wasn’t a sudden model breakthrough.” “It required a certain amount of madness... letting a model do whatever it wants on your computer.” “I experimented with this for months. Nothing bad happened.” “If you understand the technology, it’s a calculated risk.” “And the upside is so large that it’s worth it.”

Forward Future

50,502 views • 7 months ago

Anthropic is starting to ban Pro/Max accounts for using OpenClaw. Don’t risk your main account. 🛑 I’ve been running OpenClaw + Claude Code through the MiniMax M2.5 provider for $20/month. It’s "unlimited" for dev work and completely bypasses the ban wave since you’re using a dedicated API gateway. The setup: - Get the $10/$20 Coding Plan at - Grab the API key from the "Direct Account" sidebar. - Update your settings.json (Windows) or .zshrc (Mac) with the MiniMax endpoint. Claude Code (Windows): Go to ~/username/.claude/settings.json Paste your API key into this JSON: { "env": { "ANTHROPIC_BASE_URL": " "ANTHROPIC_AUTH_TOKEN": " ", "API_TIMEOUT_MS": "3000000", "CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC": 1, "ANTHROPIC_MODEL": "MiniMax-M2.5", "ANTHROPIC_SMALL_FAST_MODEL": "MiniMax-M2.5", "ANTHROPIC_DEFAULT_SONNET_MODEL": "MiniMax-M2.5", "ANTHROPIC_DEFAULT_OPUS_MODEL": "MiniMax-M2.5", "ANTHROPIC_DEFAULT_HAIKU_MODEL": "MiniMax-M2.5" } } Claude Code (macOS): In ~/.zshrc add: export MINIMAX_API_KEY="your_minimax_api_key_here" export ANTHROPIC_BASE_URL=" export ANTHROPIC_AUTH_TOKEN="$MINIMAX_API_KEY" export ANTHROPIC_MODEL="MiniMax-M2.5" Config details in the video. 👇
1:28

Anthropic is starting to ban Pro/Max accounts for using OpenClaw. Don’t risk your main account. 🛑 I’ve been running OpenClaw + Claude Code through the MiniMax M2.5 provider for $20/month. It’s "unlimited" for dev work and completely bypasses the ban wave since you’re using a dedicated API gateway. The setup: - Get the $10/$20 Coding Plan at - Grab the API key from the "Direct Account" sidebar. - Update your settings.json (Windows) or .zshrc (Mac) with the MiniMax endpoint. Claude Code (Windows): Go to ~/username/.claude/settings.json Paste your API key into this JSON: { "env": { "ANTHROPIC_BASE_URL": " "ANTHROPIC_AUTH_TOKEN": " ", "API_TIMEOUT_MS": "3000000", "CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC": 1, "ANTHROPIC_MODEL": "MiniMax-M2.5", "ANTHROPIC_SMALL_FAST_MODEL": "MiniMax-M2.5", "ANTHROPIC_DEFAULT_SONNET_MODEL": "MiniMax-M2.5", "ANTHROPIC_DEFAULT_OPUS_MODEL": "MiniMax-M2.5", "ANTHROPIC_DEFAULT_HAIKU_MODEL": "MiniMax-M2.5" } } Claude Code (macOS): In ~/.zshrc add: export MINIMAX_API_KEY="your_minimax_api_key_here" export ANTHROPIC_BASE_URL=" export ANTHROPIC_AUTH_TOKEN="$MINIMAX_API_KEY" export ANTHROPIC_MODEL="MiniMax-M2.5" Config details in the video. 👇

Ziwen

108,559 views • 6 months ago

local LLMs on Mac are getting good. but the workflow around models is still messy. you have models in: •⁠ ⁠LM Studio •⁠ ⁠Ollama •⁠ ⁠Hugging Face cache •⁠ ⁠random folders •⁠ ⁠manual downloads and every runtime expects something slightly different. we built ModelHub to clean up this layer. it’s a native macOS menu bar app for discovering, downloading, and managing local LLMs. not a replacement for Ollama, oMLX or LM Studio. it sits beside them. Ollama = run models MLX = Apple Silicon acceleration LM Studio = local model workspace Hugging Face = model ecosystem ModelHub = model discovery + management layer we’re live on Product Hunt today. would love feedback from people running local models on Mac.
1:39

local LLMs on Mac are getting good. but the workflow around models is still messy. you have models in: •⁠ ⁠LM Studio •⁠ ⁠Ollama •⁠ ⁠Hugging Face cache •⁠ ⁠random folders •⁠ ⁠manual downloads and every runtime expects something slightly different. we built ModelHub to clean up this layer. it’s a native macOS menu bar app for discovering, downloading, and managing local LLMs. not a replacement for Ollama, oMLX or LM Studio. it sits beside them. Ollama = run models MLX = Apple Silicon acceleration LM Studio = local model workspace Hugging Face = model ecosystem ModelHub = model discovery + management layer we’re live on Product Hunt today. would love feedback from people running local models on Mac.

sabesh 📟

31,497 views • 3 months ago

Kling AI has impressed me so much with the new Kling 2.0 that I've made a special compilation video to showcase my work so far. 2.0 has the best prompt adherence of any model I've experienced. This is the future! 1.6 was already good, but this is the model I've been waiting for. Everything below is a one-try output. Kling AI
1:21

Kling AI has impressed me so much with the new Kling 2.0 that I've made a special compilation video to showcase my work so far. 2.0 has the best prompt adherence of any model I've experienced. This is the future! 1.6 was already good, but this is the model I've been waiting for. Everything below is a one-try output. Kling AI

WuxIA Rocks

14,680 views • 1 year ago

I'm getting there folks... Playing with bigger opensource models and getting Sonnet-ish replies within my OpenClaw🦞 for 'free'🔥 Loaded up Qwen3.5-397b-a17b on the mac studio and after learning about MLX and LM studio for a day & finally got it working 🤓
2:45

I'm getting there folks... Playing with bigger opensource models and getting Sonnet-ish replies within my OpenClaw🦞 for 'free'🔥 Loaded up Qwen3.5-397b-a17b on the mac studio and after learning about MLX and LM studio for a day & finally got it working 🤓

Jesse Genet

56,928 views • 4 months ago

The next generation of the aircraft, a concept model called the Aerolite Spitfire Type 433, has been built by a team of designers and engineers at a fraction of the cost of buying an original. The new two-seater model has been constructed for about £750,000, compared with the more than £3 million price tag of an original Spitfire. 🔗
0:22

The next generation of the aircraft, a concept model called the Aerolite Spitfire Type 433, has been built by a team of designers and engineers at a fraction of the cost of buying an original. The new two-seater model has been constructed for about £750,000, compared with the more than £3 million price tag of an original Spitfire. 🔗

Sky News

95,593 views • 3 months ago

THIS DEVELOPER RAN THE LARGEST AI MODEL IN THE WORLD ON 5 MAC STUDIOS - AND IT COST 100X LESS THAN WHAT OPENAI USES 27:47 he says it after hours of setup - Llama 3.1 405B running locally on five Mac Studios - a model that normally requires 42 GPUs at $1,600 each or an entire data center 320GB unified memory combined - every Mac Studio adds its 64GB into one shared pool - and a model that needs 1TB of VRAM just distributes across all five it launched, it responded and not a single token went to OpenAI or Google - everything local, everything private, everything yours and 100x cheaper 5 Mac Studios, 46 watts for all of them in idle - less than one light bulb per machine what OpenAI keeps behind a subscription he ran at home with a one-time purchase in a few clicks
34:56

THIS DEVELOPER RAN THE LARGEST AI MODEL IN THE WORLD ON 5 MAC STUDIOS - AND IT COST 100X LESS THAN WHAT OPENAI USES 27:47 he says it after hours of setup - Llama 3.1 405B running locally on five Mac Studios - a model that normally requires 42 GPUs at $1,600 each or an entire data center 320GB unified memory combined - every Mac Studio adds its 64GB into one shared pool - and a model that needs 1TB of VRAM just distributes across all five it launched, it responded and not a single token went to OpenAI or Google - everything local, everything private, everything yours and 100x cheaper 5 Mac Studios, 46 watts for all of them in idle - less than one light bulb per machine what OpenAI keeps behind a subscription he ran at home with a one-time purchase in a few clicks

Noisy

21,553 views • 2 months ago

2 moms, 5 mac minis, 7 kids, infinite OpenClaw🦞 ideas This episode with Jesse Genet might be my favorite How I AI yet 🦞🦞🦞 🦞 🦞 After a tricky start, I finally found my groove with Polly the Clawdbot, and most of that was thanks to being inspired by Jesse. She shows us: - how she runs her homeschool using Obsidian, her iphone camera, nano 🍌, and openclaw - why she decided to invest in fat stacks of mac minis, for physical partitioning of her personal data - what an army of AI agents can do for a busy mom of 4 who "wants it all" Plus we talk endlessly about how AI is perfect for parents aka people "with no hands." A BIG thanks to this week's sponsor, my good friends at: 💎 Optimizely - Your AI agent orchestration platform for digital and marketing teams RUN don't walk to watch this one. 10/10 👉
0:58

2 moms, 5 mac minis, 7 kids, infinite OpenClaw🦞 ideas This episode with Jesse Genet might be my favorite How I AI yet 🦞🦞🦞 🦞 🦞 After a tricky start, I finally found my groove with Polly the Clawdbot, and most of that was thanks to being inspired by Jesse. She shows us: - how she runs her homeschool using Obsidian, her iphone camera, nano 🍌, and openclaw - why she decided to invest in fat stacks of mac minis, for physical partitioning of her personal data - what an army of AI agents can do for a busy mom of 4 who "wants it all" Plus we talk endlessly about how AI is perfect for parents aka people "with no hands." A BIG thanks to this week's sponsor, my good friends at: 💎 Optimizely - Your AI agent orchestration platform for digital and marketing teams RUN don't walk to watch this one. 10/10 👉

claire vo 🖤

117,118 views • 6 months ago

How to get OpenClaw🦞 to code for you at almost $0 costs. 1. Power your openclaw with Ollama (if you're on a mac f.e.), or with haiku or kimi k2.5 (if you're on VPS). Or pony-alpha on openrouter which I just discovered today (completely free) 2. Use the Kilo CLI for coding, since it lets you use MiniMax M2.1 for free, a very good coding model Works surprisingly well and doesn't bankrupt you
0:50

How to get OpenClaw🦞 to code for you at almost $0 costs. 1. Power your openclaw with Ollama (if you're on a mac f.e.), or with haiku or kimi k2.5 (if you're on VPS). Or pony-alpha on openrouter which I just discovered today (completely free) 2. Use the Kilo CLI for coding, since it lets you use MiniMax M2.1 for free, a very good coding model Works surprisingly well and doesn't bankrupt you

Moritz Kremb

56,200 views • 6 months ago

It’s been a while since I’ve shared any studio work. The past year has been intense, but Anam.ai is one of those projects worth breaking the silence for.
0:52

It’s been a while since I’ve shared any studio work. The past year has been intense, but Anam.ai is one of those projects worth breaking the silence for.

Ivan Garcia

13,627 views • 4 months ago

Day 7: OpenClaw 🦞 The ultimate lean way to handle OpenClaw I just fired Claude, Cursor, Gemini, and every other “Pro” AI tool today. Instead, I paid $50 for MiniMax M2.5 and routed it directly into OpenClaw and Claude Code. The result? My company now has a 24/7 autonomous workforce that never sleeps and costs less than my old setup. I used to optimize for tokens a day ago. Now I optimize for execution. I’m 25. This isn’t a hobby anymore. Things are getting real. It’s an actual company now!
0:49

Day 7: OpenClaw 🦞 The ultimate lean way to handle OpenClaw I just fired Claude, Cursor, Gemini, and every other “Pro” AI tool today. Instead, I paid $50 for MiniMax M2.5 and routed it directly into OpenClaw and Claude Code. The result? My company now has a 24/7 autonomous workforce that never sleeps and costs less than my old setup. I used to optimize for tokens a day ago. Now I optimize for execution. I’m 25. This isn’t a hobby anymore. Things are getting real. It’s an actual company now!

Ziwen

44,532 views • 6 months ago

MiniMax-M2.1 running fully local in AWQ-4Bit with full context window (170 GB VRAM w full context) - 1000~ to 16,000~ tps prefill - 100~ tps generation speeds - Opencode It’s doing real work, updating my blog with little steering or specificity. The problem with local LLMs is that they require too much steering, this means baby sitting which I don’t have the time to do MiniMax cracked the cost, intelligence, and speed challenge, I would say this is a top tier model. I run frontier models like Gemini and it just fails to call tools, in this year lol… ——————— I think glm-4.?-air is needed still. We need a viable model at each hardware entry point, a Mac M1 Ultra 192GB? is relatively cheap 5k to be able to run this model at 40 tps is a huge societal unlock. Smaller models can be good but size matters :p
3:01

MiniMax-M2.1 running fully local in AWQ-4Bit with full context window (170 GB VRAM w full context) - 1000~ to 16,000~ tps prefill - 100~ tps generation speeds - Opencode It’s doing real work, updating my blog with little steering or specificity. The problem with local LLMs is that they require too much steering, this means baby sitting which I don’t have the time to do MiniMax cracked the cost, intelligence, and speed challenge, I would say this is a top tier model. I run frontier models like Gemini and it just fails to call tools, in this year lol… ——————— I think glm-4.?-air is needed still. We need a viable model at each hardware entry point, a Mac M1 Ultra 192GB? is relatively cheap 5k to be able to run this model at 40 tps is a huge societal unlock. Smaller models can be good but size matters :p

0xSero

23,836 views • 8 months ago

I gave MiniMax M2.7 a task. It didn't just do it. It pushed back with questions. Been testing MiniMax M2.7 via Droid + MiniMax (official). Tool call for planning? Really good. The model keeps asking questions, and that makes the plan better. What I didn't expect, self-correction. When the plan and the execution drift, MiniMax notices. And fixes it. That's the kind of model behavior I want to see more of.
3:59

I gave MiniMax M2.7 a task. It didn't just do it. It pushed back with questions. Been testing MiniMax M2.7 via Droid + MiniMax (official). Tool call for planning? Really good. The model keeps asking questions, and that makes the plan better. What I didn't expect, self-correction. When the plan and the execution drift, MiniMax notices. And fixes it. That's the kind of model behavior I want to see more of.

λL-D1 | AI for Buzzer 🍉

28,044 views • 5 months ago

📢Official Announcement: Tsubasa's Chibi Customizable Model V2.0 Update is coming on June 8, 2026🗓️ Thank you all sooo much for your patience and support.💕 ✨Let's check out all the new features in V2.0✨ #TsubasaChibiCustomizableModel #live2d #Vtuber
2:04

📢Official Announcement: Tsubasa's Chibi Customizable Model V2.0 Update is coming on June 8, 2026🗓️ Thank you all sooo much for your patience and support.💕 ✨Let's check out all the new features in V2.0✨ #TsubasaChibiCustomizableModel #live2d #Vtuber

Tsubasa🫐Chibi Customizable Model V2.0 OUT

20,418 views • 2 months ago

Vertical Studio is here 🟧 The product you have been waiting for is now live Build your own custom AI model in minutes, without coding Upload any data, we’ll structure it for you, and start training instantly For now, it’s completely free for early users The future of custom AI starts now
0:37

Vertical Studio is here 🟧 The product you have been waiting for is now live Build your own custom AI model in minutes, without coding Upload any data, we’ll structure it for you, and start training instantly For now, it’s completely free for early users The future of custom AI starts now

Vertical AI

59,848 views • 10 months ago

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

109,369 views • 2 months ago

Cycle Scam How is it possible that a dealer can give a cycle cheaper than manufacturer of cycle ? It’s only possible in Delhi Govt. Because Vendor promised a superior model but is providing an inferior model of Rs 4000/- per cycle and Govt is paying the price if superior model of around 7000/- per cycle. Commission of almost 75% on cost price of 1,30,000 bicycles.
2:44

Cycle Scam How is it possible that a dealer can give a cycle cheaper than manufacturer of cycle ? It’s only possible in Delhi Govt. Because Vendor promised a superior model but is providing an inferior model of Rs 4000/- per cycle and Govt is paying the price if superior model of around 7000/- per cycle. Commission of almost 75% on cost price of 1,30,000 bicycles.

Saurabh Bharadwaj

34,023 views • 23 days ago