I ran some pelicans at the four different reasoning levels (none, low, medium, xhigh - apparently high and xhigh are aliases of each other) on a DGX Spark using Unsloth's unsloth/Qwen3.8-Flash-Next-GGUF (UD-IQ1_S):

https://tools.simonwillison.net/markdown-svg-renderer#url=ht...

Surprised I didn't get one I liked as much as the Qwen 3.8 27B one https://simonwillison.net/2026/Aug/16/qwen-38-27b/#the-defau... , maybe because of quantization.

▲

kzrdude a day ago | parent | next [-]

If I read correctly, that's based on a 1-bit quantization, and can we really expect that to produce any useful output at all?

	▲	walrus01 12 hours ago \| parent [-]
		if the goal is vector art salvador dali, like melting clocks and stuff, sure

▲

bhelkey a day ago | parent | prev | next [-]

Why did you use 1-bit quantization vs 3-bit quantization?

It looks like the 3-bit requires 90 GB[1] which, I imagine, would fit within the DGX Spark's 128GB of unified memory.

[1] https://unsloth.ai/docs/models/qwen3.8-next

▲

badatnames a day ago | parent | prev | next [-]

You should find an excuse to offer 3D printed extruded pelicans from various models as awards for something. I have no idea for what, but the idea captivates and I'd love to win one somehow. They'd be collector's items in a few decades

	▲	jononor a day ago \| parent [-]
		If Simon would pitch for example PCBWay that and I am pretty sure they will sponsor it (assuming their logo stays). They can do laser engraved versions also ;)

▲

coder543 a day ago | parent | prev | next [-]

The spark can easily run UD-Q4_K_XL on this model... using IQ1_S doesn't make much sense.

▲

simonw a day ago | parent | prev | next [-]

Tried again with a different quant, UD-Q2_K_XL:

https://tools.simonwillison.net/markdown-svg-renderer#url=ht...

▲

simonw a day ago | parent | next [-]

... and once more with UD-IQ4_XS

https://tools.simonwillison.net/markdown-svg-renderer#url=ht...