Qwen3.8-Flash-Next

whwhyb

looks like it's better than deepseek v4 flash

freakynit

Those benchmarks look seriously impressive.. considering how small of a MoE model this is.

skarz

do we really need breaking news about qwen posted every single day?

christkv

Looks like a good model for strix halo

tosh

this is a new architecture (foreshadowing qwen 4) > trained at just 1/9 the cost of Qwen3.7-Plus, while outperforming it across the board https://x.com/Alibaba_Qwen/status/2092591393424515114

rohansood15

Didn't expect it to beat 3.8 27B so cleanly. Opus 4.6 Max self-hosted at 30 tok/s on a 5k Macbook in Aug 2026. The LLM timelines are crazy.

lnenad

Adding to my homelab stack, hopefully it doesn't overthink like the little model. Actually, hoping it thinks a bit less. Wait actually I'm really praying it reasons a bit more directly. But wait, I'm really sure that it must be a bit better.

martinald

FYI: nothing seems to be able to run this (easily) yet. llama.cpp, vllm etc I couldn't get working because of no support in the mainline version.

amclennon

It looks like this also undercuts the already absurdly inexpensive Deepseek Flash in pricing. Wild.

pram

It's in Unsloth Desktop already. Looks like it's 73GB, so 128GB Mac or Strix Halo etc will work. Exciting!

KolmogorovComp

Will this be cheaper than DS4flash ?

armcat

How is input token efficiency/verbosity on this model? Has anyone tried? GLM 5.2 was doing lot of turns and thinking piling up input tokens in the context (compared to Claude and GPT models). Then Qwen3.8-27B was 2x of that. Both delivered good output results but those cumulative input token costs were not cheap. Note this is on our specific business workloads. Genuinely interested in other people's experience (if you are able to try it out).

a_humean

Waiting for llama.cpp support to land, but this might be a big deal for Strix Halo users. 6B active params helps around the memory bandwidth constraints, but a 128GB box can probably run the Q3/Q4 quants fairly easily with a decent context size. This might actually be better for strix users than 27B, which was already very good.

Imustaskforhelp

Pelican: https://gist.github.com/SerJaimeLannister/8fdef9c00175da0ca6... Aside from the pelican, I am sort of impressed by the fact that things are going the way in terms of really impressive small models. Also I love how this uses N-gram embedding. I think that Longcat was the first one who used it (I submitted that submission on hackernews because I really just loved the idea of it that I understood), I am certainly more interested in local LLM models and its interesting how they are utilizing new architectures to do some really impressive optimizations! (Do note that I created it using a free rate limited end-point that I found on the huggingface space section: https://victor-chat-with-qwen3-8-flash-next.hf.space )

andai

Father, I cannot scroll the website.

loclol101

Definitely need to try this out locally.

NooneAtAll3

what's the deal with absent scrollbar on the website?

andy99

> Qwen3.8-Flash-Next features a 125B-parameter main model, supplemented by an additional 51B N-gram embeddings, with 6B parameters activated per token. Didn’t see this mentioned yet. I wonder what this means for the effective size. It’s evidently ~176B paramètres, but how does that get quantized. A 4-bit quant under 100GB seems unlikely, I’m suspecting this won’t run in 128GB unified memory In principle I like the idea of trading more memory for compute though, even if there’s a memory shortage right now

garo-pro

Interestingly they also share the parameter count for Qwen 3.7 Plus (397 b a17b). I don't think these were known before but I might be wrong.

anon373839

Does anyone have an idea how this might perform on a DGX Spark at longer contexts? I've been trying to investigate their performance with these medium-sized MoE models, but I'm seeing a lot of incomplete and conflicting information. The 273 GB/s bandwidth looks awfully bad on paper...