It's in Unsloth Desktop already. Looks like it's 73GB, so 128GB Mac or Strix Halo etc will work. Exciting!
73GB for the 1 bit model...
Qwen3.8-Flash-Next
51–60 of 246 posts
Re: Qwen3.8-Flash-Next
#52[dead]
Re: Qwen3.8-Flash-Next
#53Adding 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.
You’re absolutely right to be hopeful. Three honest possibilities, and I’ll be straight with you about each:
1. It overthinks — Just like the previous iteration. High confidence. 2. It doesn’t overthink — Improvement from the last model for your use case. Regression for others. 3. It sometimes overthinks — Best case all around. A feature, not an impairment.
One final thing worth mentioning: (I made myself irrationally angry writing this)
Re: Qwen3.8-Flash-Next
#54what's the deal with absent scrollbar on the website?
Re: Qwen3.8-Flash-Next
#55Adding 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.
You’re absolutely right to be hopeful. Three honest possibilities, and I’ll be straight with you about each: 1. It overthinks — Just like the previous iteration. High confidence. 2. It doesn’t overthink — Improvement from the last model for your use case. Regression for others. 3. It sometimes overthinks — Best case all around. A feature, not an impairment. One final thing worth mentioning: (I made myself irrationall…
You made me irrationally laugh reading this
Re: Qwen3.8-Flash-Next
#56Earlier quoted context omitted.
This is a good counter argument. But you have to note that this is after OpenAI cut Luna costs by 80%. If you compare launch pricing, Qwen probably comes out ahead on a cost-performance basis.
The luna cost cuts were real though, not a one time promotion or something, due to some optimization (probably distillation?) that openai did.
what if it was because of quantization and they haven't released the new benchmarks for it?
Anything which changes the model needs new benchmarks I guess to compare with other models, otherwise you can benchmark Fable, and distill it to student model and keep claiming this is the Fable model
Re: Qwen3.8-Flash-Next
#57FYI: 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.
Probably going to take a 1-3 days for support to land in llama.cpp and vllm.
Re: Qwen3.8-Flash-Next
#58> 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
Re: Qwen3.8-Flash-Next
#59Earlier quoted context omitted.
For comparison with hosted models, GPT 5.6 Luna scores 67% on DeepSWE, compared to 59% here for Qwen. Luna is $0.20 / $1.20 vs $0.16 / $0.47 with Qwen.
This is a good counter argument. But you have to note that this is after OpenAI cut Luna costs by 80%. If you compare launch pricing, Qwen probably comes out ahead on a cost-performance basis.
>If you compare launch pricing
Why?
Re: Qwen3.8-Flash-Next
#60Interestingly 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.