[dead]
Qwen 3.8-Flash-Next releasing tomorrow (125B a6B)
21–30 of 178 posts
Re: Qwen 3.8-Flash-Next releasing tomorrow (125B a6B)
#22Wow. I wasn't expecting this. I thought they were going to do a 35B model instead.
As a 5090 owner and local model enthusiast, I was hoping it would be 35B A3B so I could run it myself =(.
Re: Qwen 3.8-Flash-Next releasing tomorrow (125B a6B)
#23Really happy for those with 128GB+ RAM. Sitting here with my Apple M1 Max with 64GB though. Was looking forward to a Qwen3.8-35B-A3B like many others.
Have you tested Muse Glimmer in low reasoning strength?
Token generation is slow (and prefill is) but you will likely find it solves actual problems faster than Qwen 3.6 35B-A3B.
Re: Qwen 3.8-Flash-Next releasing tomorrow (125B a6B)
#24Earlier quoted context omitted.
IDK, prefill speed is a bigger concern for most wokflows, like agent coding, and I heard that this is quite low on macs?
That was mainly before the M4 generation when they didn't have matmul instructions.
M5 prefill is much faster than M4.
I've seen benchmarks that show 4-5x faster of M5 Max vs. M4 Max.
For local models you're likely using M5 Max, prefill is low thousands of tokens per second, as opposed to, say high hundreds with M4 Max.
For larger dense models, some fraction of that, but similar multiple.
Re: Qwen 3.8-Flash-Next releasing tomorrow (125B a6B)
#25I enjoy the Qwen models a lot, but building things on top of them with OpenRouter has been painful. OpenRouter does a lot of great work and I really enjoy being able to use different models so easily. I like when a provider is phasing out an older model that still works for my needs and the price is much lower. It seems like such a good win-win. However, the problem is that many Qwen models have almost no capacity or…
The best solution to this for me is to self host litellm or a different router and use model aliases. For example I have a model called "coding" and when a new good model comes out I just switch the backend without needing to change the alias or the key in my projects (opencode, etc).
I have a few of them even a smart router called "agents" which will use local models but if it thinks the request might require higher reasoning it's routing to a different model
Re: Qwen 3.8-Flash-Next releasing tomorrow (125B a6B)
#26Time to dust off my 128GB strix halo (literally—it’s been dusty, and it’s running a bit warm these days).
Any idea where this model sits according toquality benchmarks? Pre-bubble MSRP on this hardware was $1400, and it draws 200-ish watts, putting it down into consumer territory.
I’m wondering if it can replace claude for llm-friendly coding tasks.
Re: Qwen 3.8-Flash-Next releasing tomorrow (125B a6B)
#27It will be interesting to see the intersection of this with inference engines like FreeToken which improve distribution of work for MoE models across CPU/RAM and GPU/VRAM.
If all it takes for a competitive model to run locally at good speeds is a used 3090 and some DDR4, then we might be in for the year of local AI.
Re: Qwen 3.8-Flash-Next releasing tomorrow (125B a6B)
#28gg
Well put and succinctly put. And if OxA is a flash model? it becomes: goodnight
Re: Qwen 3.8-Flash-Next releasing tomorrow (125B a6B)
#29Earlier quoted context omitted.
That was mainly before the M4 generation when they didn't have matmul instructions.
M5 prefill is much faster than M4. I've seen benchmarks that show 4-5x faster of M5 Max vs. M4 Max. For local models you're likely using M5 Max, prefill is low thousands of tokens per second, as opposed to, say high hundreds with M4 Max. For larger dense models, some fraction of that, but similar multiple.
Yes, I have the M5 Max. But there was no matmul acceleration before the M4 which made things a lot slower.
Re: Qwen 3.8-Flash-Next releasing tomorrow (125B a6B)
#30Wow. I wasn't expecting this. I thought they were going to do a 35B model instead.
As a 5090 owner and local model enthusiast, I was hoping it would be 35B A3B so I could run it myself =(.
You can run the 27B released last week. I haven't tried it yet myself but the 3.6 version runs great on my 5090.