Rendered at 16:06:55 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
osti 18 hours ago [-]
Given that DeepSwe is one of the very few coding benchmarks worth taking a look at, this achieves rather excellent result at it (not far from opus 4.8).
From looking at the results and my own impression of 5.1 and other models, I think this is the best Chinese coding model by some non-insignificant margin.
LaurensBER 18 hours ago [-]
I've been very pleased with it's performance over the last few days.
It's definitely not near Opus 4.8 level but it's very impressive nonetheless and it does do design extremely well.
ebbi 17 hours ago [-]
> it does do design extremely well
Better than Opus?
osti 13 hours ago [-]
I don't know what people mean when they say design lol, is it for frontends?
ebbi 9 hours ago [-]
Yeah, that's what I mean anyway. Each model has certain design tropes it repeats everywhere, and some of them are very old-school or not really UI best practice.
And then the more ambitious cases where you ask for a feature without being prescriptive with UI needs, the end result is sometimes atrocious with weird font use, colours, etc.
fcanesin 15 hours ago [-]
Zhipu AI is founded by a superstar Tsinghua professor, did an IPO in January (Hong Kong stock exchange) hired half it's past research lab and it's stock is >10x since. This is not a "just distill Claude" thing.
Looks like their code subscription is sold out. Clicking on the "Subscribe" button just does nothing. Pay-as-you-go API works well.
dbbk 18 hours ago [-]
If I have a fully maxed out MacBook Pro, would it make sense to just switch from Opus 4.8 to this? I've never tried running local models for coding...
entrope 16 hours ago [-]
HuggingFace says this model has 753B parameters, which will need a lot more RAM than a maxed-out MacBook Pro. With 40B active parameters, running from SSD would need patience.
_aavaa_ 13 hours ago [-]
For an fp4 quantization it should fit with room to spare for KVCache
Tepix 8 hours ago [-]
Aren't Macbooks limited to 128GB RAM?
FP4 would require >350GB RAM + KV cache, so no.
_aavaa_ 4 hours ago [-]
Oops, you’re right. My brain understood Mac Studio for some reason.
api 16 hours ago [-]
I’ve wondered for a while if anyone is working on very wide channel parallel (kind of like RAID 0) SSD for this purpose. Couple that with a tensor processor and that would be interesting.
petu 8 hours ago [-]
There's talks about HBF. F for Flash -- HBM packaging and bus width, but using NAND memory.
From looking at the results and my own impression of 5.1 and other models, I think this is the best Chinese coding model by some non-insignificant margin.
It's definitely not near Opus 4.8 level but it's very impressive nonetheless and it does do design extremely well.
Better than Opus?
And then the more ambitious cases where you ask for a feature without being prescriptive with UI needs, the end result is sometimes atrocious with weird font use, colours, etc.
It it normal for startup in China?
FP4 would require >350GB RAM + KV cache, so no.
e.g. https://www.sandisk.com/company/newsroom/press-releases/2026...
And previously: https://news.ycombinator.com/item?id=48518684