this post was submitted on 29 May 2025
158 points (90.7% liked)

Technology

70528 readers
4903 users here now

This is a most excellent place for technology news and articles.


Our Rules


  1. Follow the lemmy.world rules.
  2. Only tech related news or articles.
  3. Be excellent to each other!
  4. Mod approved content bots can post up to 10 articles per day.
  5. Threads asking for personal tech support may be deleted.
  6. Politics threads may be removed.
  7. No memes allowed as posts, OK to post as comments.
  8. Only approved bots from the list below, this includes using AI responses and summaries. To ask if your bot can be added please contact a mod.
  9. Check for duplicates before posting, duplicates may be removed
  10. Accounts 7 days and younger will have their posts automatically removed.

Approved Bots


founded 2 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
[–] vhstape@lemmy.sdf.org 27 points 4 days ago (2 children)

the Chinese AI lab also released a smaller, “distilled” version of its new R1, DeepSeek-R1-0528-Qwen3-8B, that DeepSeek claims beats comparably sized models on certain benchmarks

Most models come in 1B, 7-8B, 12-14B, and 27+B parameter variants. According to the docs, they benchmarked the 8B model using an NVIDIA H20 (96 GB VRAM) and got between 144-1198 tokens/sec. Most consumer GPUs probably aren’t going to be able to keep up with

[–] avidamoeba@lemmy.ca 7 points 4 days ago (1 children)

It proved sqrt(2) irrational with 40tps on a 3090 here. The 32b R1 did it with 32tps but it thought a lot longer.

[–] vhstape@lemmy.sdf.org 2 points 4 days ago* (last edited 4 days ago)

On my Mac mini running LM Studio, it managed 1702 tokens at 17.19 tok/sec and thought for 1 minute. If accurate, high-performance models were more able to run on consumer hardware, I would use my 3060 as a dedicated inference device

[–] brucethemoose@lemmy.world 2 points 3 days ago* (last edited 3 days ago)

Depends on the quantization.

7B is small enough to run it in FP8 or a Marlin quant with SGLang/VLLM/TensorRT, so you can probably get very close to the H20 on a 3090 or 4090 (or even a 3060) and you know a little Docker.