Hacker News new | ask | show | jobs
by roadside_picnic 22 days ago
What's the tokens/sec you're getting on that setup (genuinely curious because it's a setup I haven't actually run myself)?
1 comments
wolttam 22 days ago
Using regular DeepSeek-V4-Flash, I see 2000tok/s prompt processing and from 40 to 50 tok/s generation. Performance doesn't drop much at long contexts, DSv4 is really nice for that.

With DeepSeek-V4-Flash-DSpark (Deepseek's new speculative decoding scheme), which is still barely supported anywhere, we're seeing a more steady 45-55 tok/s with bursts into the 60s.

link
roadside_picnic 22 days ago
> from 40 to 50 tok/s generation

That's actually much better than I would have thought!

Thanks for the answer and it does make this approach make more sense as a budget solution to running larger models locally.

link
verdverm 21 days ago
What quant size are you using? Just picked up my second spark and a cable and wanted to try this one out for fun. I generally run a bunch of models for different purposes (easy / bulk tasks) and use APIs for harder tasks.
link
wolttam 20 days ago
It's the native DeepSeek V4 Flash quant which is released in MXFP4. You have enough RAM left over with 2 sparks for ~2M tokens of working KV cache.
link