20 cards booting up what to mine?

Looking to hire someone full-time to help with chasing this year Mid to late April through June. Filming, livestreaming, navigation, and helping keep everything running smoothly Paid role — must be okay with relocating to Minnesota for the season More details at the link below! Apply here 👇 forms.gle/DeK1JcRtH7qqQhtTA

Buying as many phones as I did was well worth the agents I’m able to run! Fun times!

unacoin will be more friendly to mine on laptops with arm cpus/phones due to us changing how fast block difficulty is removed when not needed

Go give this a watch! only Pre-Build Code is live rn! @Cellhasher

Benchmarked DeepSeek Coder 1.3B Q4_K_M on @Cellhasher vs llama.cpp vs @tether / @paoloardoino qvac today. Single phone 5yr old(Adreno 660, 4 threads): First Number = Prompt tok/s Second Number = Generation tok/s - llama.cpp (b8156): 66.35 / 25.88 tok/s - qvac-fabric: 55.53 / 26.56 tok/s - cellswarm-v2: 62.02 / 28.20 tok/s 🔥 Takeaways: llama.cpp still wins on prompt speed qvac gains slightly on generation Cellhasher leads overall on generation throughput Results are close, but Cellhasher edges it out where it matters. What model should we test next? Qwen3.5 coming once (tether supports it) qvac rebases 👀

Cellhasher is so far ahead, but cant get the modern news... infact our software on phones is much faster and more advanced than @tether @Cellhasher for AI

x.com/wabdoteth/status/20311… Sorry @wabdoteth we needed to give this a try.

Good for Cellhasher! This is needed

The way this works is like crypto spec mining. The people who will get the fastest ROI are the day 1 movers, getting your fleet deployed ASAP in your region. More and more people join and the cost of timeshare goes down and down as more people join the network. It will work for the people who are able to get vehicles first. The best way to bring your cost down is to actually use a business formation, make content to write off more, the content will provide some income as it’s something new and people who don’t take risk will sit and watch and make you income while your fleet makes income. Then as things start to dwindle down if you can’t scale asap, then you’ll be able to ROI and sell the fleet.

Roadmaps are free. Code is not. Nintondo ships code. 39,000 commits on Bellscoin core alone. 25 public repositories. Rust. TypeScript. C . MIT and CC0 licensed - anyone can verify, fork, and build. No closed-source black box. No "trust us, it's coming." Just open-source infrastructure for Bellscoin, Dogecoin, and Pepecoin. Don't trust. Verify. Nintondo on GitHub.

RIP Agent Hustle🥷we're pulling everything under the Emblem brand and token $HUSTLE TLDR - Agent Hustle is now EmblemAI - $HUSTLE migrating to $EMBLEM - $EMBLEM to power the entire ecosystem -> EmblemAI, @EmblemVault, @MigrateFun, Emblem Developer Platform, and AI wallet for agents

Here are Android AI @Cellhasher Qwen3.5 DeepSeek 33B benchmarks. TLDR: its actually worth it if you have old androids for the cheap less than 5w most of these phones operate at. Especially as agents become more deployable and 24/7 hands off or sit and forget. AI model companies will eventually start fine tuning even further to get models into more of a MOE style but tuned directly to the use with Routers, routing each request. Cellhasher is working on this as well. As demand for compute and energy continues, eventually companies will not keep making bigger models and not Company can keep pace with the big ones, they will focus on small local models for retail. We will start with the 5 year old Chipset and Bring you up to speed with some wild results on a newest-chipset. Device: Snapdragon 888 (5 years old chip) CPU only Non-root (28 GB/s memory cap) Rooted devices (56 GB/s) scale ~1.8–1.9x. (using the fastest 4 cores actually outperforms using all 8 cores) Qwen3.5 - 0.8B CPU (4 big cores): 12.54–13.01 tok/s Rooted (1.8–1.9x): 22.6–24.7 tok/s Vulkan GPU (NGL=24): 1.60–1.78 tok/s (7–8x slower) Qwen3.5 - 2B CPU (4 big cores): 9.15–9.36 tok/s Rooted: 16.5–17.8 tok/s Vulkan GPU (NGL=24): 0.78–0.86 tok/s (11–12x slower) Large Models (Non-Root) #p stands for Number of Phones in a parallel pipeline ring made by Cellhasher Swarm AI DeepSeek 33B → 5.89 tok/s (Best was 7.8 tok/s) average is still 5.89 tok/s (12p, d=16, 81% accept) Qwen3.5-35B-A3B → 3.75 tok/s (best was 5.1 tok/s) (3p, d=8, 71.5% accept) Qwen3.5-32B (Coder) → 2.85 tok/s (best 4.8 tok/s) (7p, same-family draft) Rooted Estimate (56 GB/s) DeepSeek 33B → ~10–11 tok/s Qwen3.5-35B → ~6.5–7 tok/s Qwen3.5-32B → ~5–5.5 tok/s Snapdragon 8 Elite Gen 5 plus 24gb RAM (Android Phone) ~75–85 GB/s memory bandwidth INT4/INT8 NPU usable Well-tuned pipeline Qwen3.5 - 0.8B Model CPU only: 30–45 tok/s CPU NPU: 70–100 tok/s Qwen3.5 - 2B Model CPU only: 18–25 tok/s CPU NPU: 40–60 tok/s DeepSeek 33B CPU only: 15–20 tok/s CPU NPU (blended): 20–28 tok/s (30 tok/s possible with ideal tuning) Qwen3.5-35B-A3B CPU only: 11–15 tok/s CPU NPU: 16–22 tok/s Qwen3.5-32B (Coder) CPU only: 10–14 tok/s CPU NPU: 15–20 tok/s (CPU NPU is slightly tricky and prefill along with ring pipeline can determine alot, KV cache catching is something i haven't played around with yet) 33B class ~2.5–3.5x over Snapdragon 888 Small models see major NPU uplift Memory bandwidth remains the limiter on large models @Cellhasher has come along way driving inspo from @exolabs over the last few months although things needed to change in order to be correctly managed for android really none of the EXO features are now used, we have our own modification to llama.cpp that overs this ring pipelined parallelism for running LARGE models across however many phones it takes. What's hard is sometimes less phones doesn't always compute to high tokes as some would think less hops will do the trick, in some cases it does other cases like Spec drafting sometimes it doesn't. Regardless Automously running agents 24/7 if i Can run a 80b model at 1-5tok/s on 5 year old Android hardware that runs at 5-15w depending on the amount of phones used, ill take it. If you make the upgrade to the latest generations of phones you get to experience amazing breakthrough of NPU sync and bandwidth optimization that can get you that amazing 20-70 tok/s feel depending per model for every day use. And now im thinking about taking the plunge into 20 of these new phones 20k for 160cores, and 480gb RAM i could possible run the latest and greats at maybe speeds of 10 tok/s.... who knows let me know if you want me to try! (All Phones benchmarked on Ethernet as it offers the best latency over Wifi) (Wifi Still works just slower)