Viewing profile — Tepix
Tepix
HN member- Joined
- Mon, Aug 19, 2013, 9:32 AM UTC
- HN karma
- 13,892
- Public activity
- 6,145 items
- HN profile
- View on Hacker News ↗
About Tepix
I do not use this alias anywhere else.
Got something cool? Get in touch at username at altmails.com
Recent public activity
-
comment
Comment #49219270
An infinite number of data centers even!
-
comment
Comment #49219247
Are you talking about S or XS? S is too large for a 3090 at 118b parameters.
-
comment
Comment #49206748
The license is clear. Your post merely adds to the FUD.
-
comment
Comment #49201144
That‘s the same price as a Keyboardio Model 100 which is split, wooden and has sculpted RGB backlit keys. Whoah. That said, big fan of that volume button!
-
comment
Comment #49183264
Privacy is often a requirement.
-
comment
Comment #49177848
Addendum: I was wrong, you‘ll need two of these cards.
-
comment
Comment #49173856
Yes. It's called REAP and from what I've seen, results aren't stellar.
-
comment
Comment #49173833
For sure if you want to properly utilize the model with several users in parallel and large context you'll want two MI350P.
-
comment
Comment #49168718
If you have 2x DGX Spark it will run quite nicely. They cost only $8000 or so and use less power so you may be able to rent them cheaper than the MI300X. I found an offer to rent t…
-
comment
Comment #49168702
Unfortunately, the MI300X is an OAM module. The MI350P is the one you want: It's a PCIe card, but it has less memory: 144GB. Luckily, DeepSeek V4 Flash will run in 144GB too becaus…
-
comment
Comment #49168581
I share the author's sentiment. But I have another hatred: Monospace fonts in blogs. Monospace makes text harder to read and ugly. It was a necessity. It no longer is. Get over it.…
-
comment
Comment #49165179
Latent space is calling the whole subject "inference engineering" in their episode https://www.latent.space/p/inference-eng
- comment
-
comment
Comment #49165169
Well, INT4 is good enough apparently and it's very fast.
-
comment
Comment #49165167
The latest Latent.Space episode https://www.latent.space/p/inference-eng
-
comment
Comment #49165158
vLLM tested with Llama-3.3-70B-Instruct, Qwen3-30B-A3B-Instruct-2507, Qwen3-30B-A3B-Thinking-2507, and Qwen3.5-27B. I'm wondering if it needs to be tested with every other model or…
-
comment
Comment #49164421
It uses javascript. Still a static file. Lets you play chess
-
comment
Comment #49155674
Put it on a boat, navigate to an area with a current away from any land and then slowly release it
-
comment
Comment #49153946
Why is there no orange? The entire colour palette is a bit depressing. Also my terminal (Ubuntu in WSL2) had an ugly colour palette defined by default with several identical colour…
-
comment
Comment #49151745
I consider less than 4bit to be too poor quality usually. Got any benchmarks to measure quality?
-
comment
Comment #49151736
Workaround: reduce font size on iPhone SE
-
comment
Comment #49122933
Yes, the Dual DGX Spark looks like the sweet spot for this model for now. Good preprocessing speed. Lots of context. Fast enough for 1-5 devs perhaps. Around 8200€ as of today (use…
-
comment
Comment #49122870
DS4Flash has 284B weights. 64GB? No go.
-
comment
Comment #49122853
Do they do other things with the data, like selling it?
-
comment
Comment #49121629
Why mention it? Just download the weights when they become available.