Cellhasher @Cellhasher

Tonight’s Project! Onboarding my remaining 16 Phones onto @Acurast with my @Cellhasher for AI Compute Learn More About Acurast youtu.be/HiXb0n3UUys

🎁Congrats to KayTrim for winning the @Cellhasher Kit Giveaway! Please email me at [email protected] This Giveaway was part of the video "Use your PHONE for Ai and Get Paid in Crypto!" youtu.be/HiXb0n3UUys?si… @Acurast

@oliverhenry Bro need a @Cellhasher ??

Go watch @HobbyistMiner setup Acurast on his Cellhasher. youtu.be/HiXb0n3UUys?si…

Here's an Up to date Breakdown on @Cellhasher with @YourFriendAndy Code: ANDYSFRIENDS at checkout for DIY! Code: ANDY at checkout for Pre-Built Units! Watch it here: youtu.be/EUyRA5CcdMU

@Chain_AlphaX @paoloardoino been a thing on @Cellhasher for a long time now actually!

keyboard_arrow_left Previous keyboard_arrow_right Next

New day new drop youtu.be/teNGtEWj5B0?si… we got a little @Cellhasher review 👀

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

wab.eth @wabdoteth

3 months ago

how much abstract xp do you get for rank #1? jokes aside (it's not a joke @0xCygaar pls give xp), super polished, great sfx and vibe curation esp for a browser game

52 8 216 17K 7

Something is coming to Acurast. Every block. Every deployment. Every transaction. Fully visible. Soon. 👀

@crusnikpt @Acurast 👀

Wait till everyone finds out with @Cellhasher you can deploy your 20phone cluster into an full R&D Lab with various different agents, Research, Security, Audit, Routing, Senior Engineer, Vision, func-call, dev-01 developer dev-02 developer dev-03 developer gateway developer1 guard developer senses developer reviewer meta_engineer research devops data-analyst multilingual writer scout reasoner nanbeige hot-spareguard

Imagine what happens when you use 20 phones all cooking at 10-20 token/s running 24/7 working for you Here is a taste of one Android Phone, a simple deploy of QWEN3.5 running on a 5 year old Android. @Cellhasher

@lukewrightmain Low end compute is amazingly useful even in an ever advancing Tech Sector. Phones have their place!

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)

keyboard_arrow_left Previous keyboard_arrow_right Next

Qwen @Alibaba_Qwen

3 months ago

🚀 Introducing the Qwen 3.5 Small Model Series Qwen3.5-0.8B · Qwen3.5-2B · Qwen3.5-4B · Qwen3.5-9B ✨ More intelligence, less compute. These small models are built on the same Qwen3.5 foundation — native multimodal, improved architecture, scaled RL: • 0.8B / 2B → tiny, fast,

911 3K 21K 9.0M 14K

@lukewrightmain @danieldalen @claudeai Our software supports this, A few more updates for 1-2 click deploys will come in this week as-well! Fun times, Helping people who are just getting started.

@MightyBuddha01 they look so cool, it makes it worth it!

What it feels like to have phone compute in a market turn like today!

@rukasufall @tengyanAI @openclaw Let us know if you need help. We have 1 click solutions to this :)

Join up

Cellhasher has a space today with Acurast. We don’t do spaces very often so please come check it out. Should be to long and should have some great convo and topics!

Cellhasher @Cellhasher

4 months ago

Join Us Tomorrow 1pm EST with @Acurast! Here from speakers @HobbyistMiner, @dspillere , and @Gr8erGoodMining . As we discuss democratizing compute! (link below to set a reminder) x.com/i/spaces/1kvJp…

4 6 23 3K 2