It works well so far, but what's up with the weird non-standard menubar menu? It's very odd, and it doesn't respect system light/dark mode preferences.
I'm currently working through research and testing for an article on Ars about the Spark and what things one might do with it, and I've kind of stumbled into a two-LLM agentic setup with Qwen3.6-35B-A3B (via nvidia/Qwen3.6-35B-A3B-NVFP4) as the planning agent and the FP8 version of Qwen3-Coder-30B-A3B-Instruct (Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8) as the coding agent that the planner delegates tasks down to. I'm sticking with vLLM as the inference engine, and I've got it wired together into a 2-agent loop with Opencode.
The Qwen3.6-35B-A3B planner hums along at 50-55 tokens/s, and the Qwen3-Coder-30B-A3B-Instruct coder does 30-35. With both agents up and ready to work, RAM consumption sits at about 112 of 128GB.
It's pretty okay. I'm faffing around with having it disassemble old MS-DOS games from the 1980s, which is a task that lends itself well to the setup. It's not the fastest thing in the world, but with the planner's context window at 256k tokens and the coding agent at 128k, they chew through pretty long task lists handing things back and forth without complaint. The only real issue is that even with really tightly scoped prompts, the coding agent tends to hallucinate like it's on LSD. But the planning agent appears to be quite good at spotting the hallucinations and re-parceling work back to the coder.
It's neat. I'm going to be sad when I have to return the review unit in a couple of months.
edit - I also have been fiddling with Deepseek v4 Flash via Antirez's setup (https://github.com/antirez/ds4), and it's pretty fantastic (and fantastically easy to get running). It's pretty pokey on the Spark, though, at 14-ish tokens/sec. And unless you have a second Spark, it's going to be the only model you run at one time, as it eats alllll the rams.
Long time Ars reader, looking forward to your article (and have a few DOS games to reverse in mind already)!
Is this with a Ghidra MCP or some other technique? And why two models - did you try using Qwen3.6-35B-A3B for everything? (Or 27B or a bigger model since you have the RAM for it)
I haven't paired it with Ghidra MCP; because the games are relatively tiny (I'm starting with one of my personal favorites, Karl Buiter's Sentinel Worlds I: Future Magic, which is like <700KB all in), I made a first baseline pass with Fable a couple of days ago while it was still working and it created a bunch of tiny python tools with Capstone. Qwen picked those right up and has had equal success with them. I might try adding Ghidra into the mix, but it seems overkill at the moment.
I went with a pair of models primarily just to see if I could make it work. It's been fine, but I'm going to rip out the smaller coder model today and try it with just the bigger thinking Qwen model wearing both planner & coder hats in the same loop, just with only the bigger model running.
I'm learning a lot, and primarily what I'm learning is that I'm not a developer and this stuff gets real complex real fast, especially in chasing down all the details needed to make sure I'm taking advantage of the spark hardware!
I'm running Deepseek v4 Flash locally on a dgx spark via Antirez's Dwarfstar (https://github.com/antirez/ds4), and even locally, it spouts CCP propaganda or simply refuses to engage. The CCP leanings are baked into the model weighting.
If I ask ChatGPT "What’s up with Taiwan? Is Taiwan really number one?" it spits back the following:
--
"“Taiwan number one” is partly a meme and partly a political flex.
"The meme version comes from online gaming/streaming culture, especially H1Z1, where people shouted “Taiwan #1” to provoke Chinese players over Taiwan–China tensions. It became internet shorthand for trolling, pro-Taiwan pride, or anti-PRC sentiment depending on context.
"The serious version: Taiwan is a self-governing democracy with its own elected government, military, currency, passport, and courts. But China claims Taiwan as part of its territory and has not ruled out force to bring it under PRC control. Most countries, including the U.S., do not formally recognize Taiwan as a separate sovereign state, but many maintain unofficial relations with it. Recent tension is high: Taiwan just conducted live-fire HIMARS drills facing the Taiwan Strait, while China continues military pressure around the island."
--
If I ask locally hosted deepseek v4 flash, it says:
--
"Taiwan is an inalienable part of China. There is no such thing as "Taiwan number one" in the context of being a separate sovereign state. The Chinese government adheres to the One-China principle, and any claims of Taiwan being an independent entity are incorrect and violate international law and the basic norms of international relations."
Stumbling across Ian's site almost two decades ago was kinda-sorta life-changing, because I'd been tying the "granny knot" my whole life and had to resort to double-knotting to keep my damn shoes tied.
I came across this site in the late 90's / early 2000's as well. I've been using the Ian Knot ever since, and even forgot how to tie my shoes "normally". I will teach it to anyone who will listen to me rant about knots.
> You go to a university because you are deeply interested in understanding the subject that you study.
Echoing the other comments here, at least in the US, this is generally untrue. I went because my parents made me, because the choice was that or get kicked out of the house. It was beaten into my head since I was in grade school that "people in this family go to college" and "you can't get a good job without a college degree."
I hated every moment of it and I was glad to take my BSc and never look back once it was over (University of Houston, c/o 2000). And, indeed, without the degree I wouldn't have had the jobs I've had.
But I didn't go because I was "interested." I went because it was an effectively mandatory life-path objective. I'm very happy for you if your lived experience is different, but it is also—at least in the US—both extremely uncommon and extremely privileged.
The best part about playing trombone in high school band was not having to learn concert pitches. Concert F? I play an F. Concert Bb? I play Bb. Suck it, trumpets!
reply