logoalt Hacker News

Qwen 3.8 27B

408 pointsby erdaltopraktoday at 3:00 PM301 commentsview on HN

Comments

expedited123today at 3:14 PM

Kinda was expecting to see Gemma 4 26B in benchmark comparisons :(

show 1 reply
altruiostoday at 3:14 PM

remember to let llama.cpp catch up to anything new in this model. Save your judgment until about 2 weeks of use.

show 1 reply
davidwtoday at 5:19 PM

I don't know much about the production of these models. How hard would it be to 'fork' something like this and have it not be full of CCP indoctrination?

show 1 reply
filuptoday at 3:47 PM

https://news.ycombinator.com/item?id=48403639

my prediction was way too far out. 4.6 at home! Woo.

lossolotoday at 5:09 PM

Why weren't the points merged again from the "dupe" thread that had 289 points?

https://news.ycombinator.com/item?id=49299684

What a weird mechanism. If someone is judging a thread/topic/event impact by the number of points it got, then doing this unfairly degrades that thread.

It should have deduped by user and combined the 168(at the time of writing this comment) + 289 points. Just add the twitter link from the previous thread as an additional link in the description, like you normally do, move all the points over, and remove the old thread.

naaskingtoday at 5:07 PM

Can anyone confirm whether this new Qwen release is any more concise when thinking? Overthinking was the biggest (only?) downside of the Qwen models.

brcmthrowawaytoday at 3:25 PM

This with ddg mcp to fill in world knowledge. Are local models the future when computer architectures catch up?

tristortoday at 4:59 PM

I'm hoping to see folks distill this with current generation Opus / Fable reasoning traces. I have had my best results locally so far from Qwopus (Qwen 3.6-27B w/ Opus 4.6 reasoning distilled). This looks GREAT and I am definitely setting this up later today.

alpha_triontoday at 3:16 PM

NICE, i've been waiting for this drop, thanks for posting this

Mr_Eri_Atlovtoday at 3:38 PM

This is the homelab model hands down

brcmthrowawaytoday at 3:11 PM

My Strix Halo is about to go overdrive!

cmrdporcupinetoday at 4:46 PM

I found this kind of amusing while running it (using Pi as the harness). Don't know if this is evidence of intense fine tuning from Claude but it smells like it...

" The user wants me to explore the repository at XXXX and report back. Let me start by understanding the project structure, reading the CLAUDE.md file, and getting a general overview of what this repository is.

Let me start by reading the main project documentation and exploring the directory structure.

I'll take a look around this repo. Let me start by getting a lay of the land.

read resource CLAUDE.md (ctrl+o to expand)

ENOENT: no such file or directory, access 'XXXX/CLAUDE.md'"

ramon156today at 3:28 PM

need another fable uncensored merge with 3.8, really curious what it can deliver

dude3today at 6:31 PM

[flagged]

ggerganovtoday at 6:28 PM

[dead]

RobertasTatoday at 4:24 PM

[flagged]

fintunertoday at 4:13 PM

[flagged]

steffi_olivertoday at 4:50 PM

[flagged]