[flagged]
Qwen 3.8 27B
91–100 of 848 posts
Re: Qwen 3.8 27B
#92One thing a lot of people don't seem to factor when hyping Qwen is how much models like this tend to 'overthink' with seemingly endless 'second guessing'. 3.8 seems no different from what I've tried thus far. As capable as it is, it's hard to justify using it when a competing model (e.g. Gemma4:26b-a3b) can consistently achieve the same or similar response with only 1/10th as many 'thinking' tokens, achieve much high…
gemma4 can't hold a candle to 3.6
Re: Qwen 3.8 27B
#93Can anyone who has that specific personal test he tries on different models , and tries this model , to tell us here if possible , how good or bad is this new model ? compared to others ? I only trust those users genuine personal tests
There is a down to earth guy on YT that performs a series of tests against LLMs running on non-god-tier commodity hardware. He will likely be testing this soon enough. https://www.youtube.com/@lukesdevlab I don't know if that is what you are looking for or not and as always your experiences may be different.
thaaanks man, this channel seems really informative, although < 10K subs only !
Re: Qwen 3.8 27B
#94Why don't qwen/alibaba host the model themselves? I was looking forward to trying it on their coding plan. Google are the same way with their Gemma models.
Re: Qwen 3.8 27B
#95One thing a lot of people don't seem to factor when hyping Qwen is how much models like this tend to 'overthink' with seemingly endless 'second guessing'. 3.8 seems no different from what I've tried thus far. As capable as it is, it's hard to justify using it when a competing model (e.g. Gemma4:26b-a3b) can consistently achieve the same or similar response with only 1/10th as many 'thinking' tokens, achieve much high…
You can add a thinking budget thats not much effort in llamacpp. You can align the cut off message with your agent instructions.
What you describe is a engineering harness problem.
If you, and i mean the royal you, actually read tge thinking traces you can see and figure out where its stuck
This means an effective harness would observe when the model is overthinking and step in with reasonable redirection, like increasing logging.
Llamacpp can set reasoning budget and message per reauest, so it can be dynamic.
Your complaint is "skill issue" based and will be resolved by people who do something ither than vibe code react demos.
Re: Qwen 3.8 27B
#96I use the Qwens as a vision model for my DeepSeek V4 Flashes to handle. But the Qwens run on old RTX A6000 Ampere. Does anyone know if there's any news about INT4/AWQ quants for the RTX A6000?
Re: Qwen 3.8 27B
#97Architecture thread! Afaict they continue to use gated attention + delta net, which was also adopted+adapted by K3, but im surprised theres no improvements to the residual stream (deepseek are using manifold hyper-connections, kimi have attention residuals) ? Perf improvements seem to all come from training?
As was the case with GLM 5.3, it seems that there is still much juice to be squeezed from post-training
Re: Qwen 3.8 27B
#98Earlier quoted context omitted.
> Beats Opus 4.7 Max I'm a huge open model fan, and have used them since forever, even have daily drivers for on-prem dev, but no. They do not beat opus on real-world usage. Qwen models are impressively good for what they are, are "good enough" for plenty tasks, can be ran locally on decently priced hardware, and so on. They certainly have their uses, and the field in general has advanced faster than my early expecta…
> ...but no. They do not beat opus on real-world usage. I agree, but then we just need meaningful benchmarks that clearly show that! Otherwise it's hand waving about something that should be put on paper in quantifiable terms.
In the end, the only benchmark that matters is your own.
Re: Qwen 3.8 27B
#99Wow. Speed improved as well. 200t/s on a RTX 5090!
Re: Qwen 3.8 27B
#100Earlier quoted context omitted.
There is a down to earth guy on YT that performs a series of tests against LLMs running on non-god-tier commodity hardware. He will likely be testing this soon enough. https://www.youtube.com/@lukesdevlab I don't know if that is what you are looking for or not and as always your experiences may be different.
thaaanks man, this channel seems really informative, although < 10K subs only !
It's a relatively new channel - but yeah - I feel the guy puts a lot of effort into what he does and deserves more subs.