Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
PeterStuer
5 months ago
|
parent
|
context
|
favorite
| on:
Open models by OpenAI
I love how they frame High-end desktops and laptops as having "a single H100 GPU".
organsnyder
5 months ago
|
next
[–]
I read that as it runs in data centers (H100 GPUs) or high-end desktops/laptops (Strix Halo?).
xyc
5 months ago
|
parent
|
next
[–]
I'm running it with ROG Flow Z13 128GB Strix Halo and getting 50 tok/s for 20B model and 12 tok/s for 120B model. I'd say it's pretty usable.
organsnyder
5 months ago
|
root
|
parent
|
next
[–]
Excellent! I have a Framework Desktop with 128GB on preorder—really looking forward to getting it.
phh
5 months ago
|
prev
|
next
[–]
Well if nVidia wasn't late, it would be runnable on nVidia project Digits.
PeterStuer
5 months ago
|
parent
|
next
[–]
Yes, they are late to the party. Maybe they do not want to eat into the RTX Pro 6000 sales. In the meantime, there is the AMD Ryzen™ Al Max+ 395.
robertheadley
5 months ago
|
prev
|
next
[–]
I actually tried to ask the Model about that, then I asked ChatGPT, both times, they just said that it was marketing speak.
I was like no. It is false advertising.
piskov
5 months ago
|
prev
[–]
Don’t forget about mac studio
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: