@MaxTechOfficial
Congrats on 300k subs!
@tarangsharma2898
My God!! that's a good editing(Zooming in & Zooming out focusing on text). Keep up! Great video!
@mehregankbi
Ever since the model was released, i knew this vid was coming. tonight I checked the feed for this vid on ur channel, couldn't find it and five mins later, it's on my home feed.
@mortysmith2192
The brain bit is the cutest thing I’ve ever seen 😊
@AsisVendrell
Now I'm really excited to make full use of my M1 max with 64Gb of RAM, choosed the 43Gb deepseek-r1:70b version, and it is amazing to see it working locally even though is notably slower than the web, this is fantasy come true!
@youranonymous931
You have one of the best channels on YouTube. I dont usually "join" a channel, but week by week you always amaze me.
@chandebrec5856
You are not installing "DeepSeek R1" on all those Macs. You're installing a smaller model, based on a Llama or Qwen model, that is distilled from R1.
@nisarg254
I am from India its 4am here saw your video and just installed Lm studio Man thanks for making this video
@davehachey3888
Hey, thanks. Great introduction to running LLMs on Mac hardware.
@ChristinaWarren
Was literally setting this up earlier today on my M3 Max and was curious about perf on other machine types so this is awesome! Great video as always!
@RTXON-h1h
FINALLY incredible video I love AI on mac + software engineer with deepseek R1 to make a local AI work is really worth it next time try to destroy your M4 max 128gb with the largest llm deepseek R1 you can put
@JohnLark-k9y
Excited to see you use MLX and talk about quantizisation, as a macbookpro m3 Pro chip, i want to look a little into MLX and quantisiation, would be amazing if you did some videos on those!
@GetzAI
Definitely worth double! 😃
@andrewmerrin
You are truly doing gods work! I’ve been thinking about exactly this since the models dropped.
@SamMeechWard
I'm just going to binge watch all your llmv videos now
@envt
I love your video's, this one was a bit too fast and chaotic for me. Keep up the good work 😊
@macsoyyo
I’ve run 14b version ( almost 10 Gb) ollama in a MacBookPro M2 16Gb . It runs slow but ok. Impressive results, to be honest
@beauslim
You read my mind and made the video I was looking for.
@EliWSeiei
20:48 When analyzing ram usage and power, I recommend macmon, you can even “brew install macmon”, it gives you power usage individual and total, ram usage, swap, e & p core usage
@AZisk