Friday’s big release wasQwen 3.8 27B, an Apache 2 licensed 27B parameter vision-capable LLM from Alibaba’s Qwen research lab. I’ve been looking forward to this one: 27B is an excellent size for running a model on a reasonably specced laptop, and its predecessorQwen 3.6 27Bwas impressive.
Qwen’sself-reported benchmarksfor this model are eye-opening. They show a boost from both Qwen 3.6 27Bandthe closed-weight Qwen 3.7-Plus, which was one of Qwen’s strongest models of any size as recently asMay this year. It will be interesting to hear what independent benchmarks have to say about the model.
I’ve been running the model on two different machines: my 128GB M5 Max MacBook Pro, and anNVIDIA DGX Spark. On both machines I’m running LM Studio andtheir 17GB Q4_K_M quantized build. I also tried usingllama-serverdirectly on the Spark.
Qwen’s documentation describes the model as defaulting toxhighfor the reasoning effort, and the LM Studio GGUF I’ve been trying preserves that default:
Qwen3.8 comes with official support forreasoning_effort, which can be used to adjust reasoning depth and control cost:
This is ahilariousdefault. It’s absolutely not a good way to run the model, especially on consumer hardware. I’ve been finding the results extremely entertaining.
I quickly ran into problems with LM Studio’s default context limit of 8,192 tokens—Qwen was using them all up thinking about even the most mundane of problems. I loaded the model with the full 262,144 maximum context length and that problem went away.
Here’sthe pelican riding a bicycleSVG I got from my first attempt with that increased context length. It took21 minutesto generate, using 22,276 reasoning tokens to produce 3,223 tokens of output. You can readthe reasoning trace here.
This is by far the best pelican SVG I’ve been able to generate with a model that runs on a local machine—and this Qwen is pretty small, just a 17GB file on disk. There’s a lot to like about this:
Was that worth waiting 21 minutes for? Absolutely not.
Here’s that same prompt run with reasoning turned off—transcript here. This one produced3,715 tokensand took 137s—just over two minutes.
And just for completeness, I used OpenRouter to run the same prompt through the much larger Qwen 3.8 2.4T-A95B (releasedlast week) and got this snazzyanimated SVG: