A home for GPU miners and builders. Mainnet is live. Building toward customer-paid AI inference. Follow for setup help, releases and progress.
United States
Joined August 2026
- Tweets469
- Following21
- Followers787
- Likes175
Pinned Tweet
Common Foundry: We unlocked nearly 2× FP8→FP32 Tensor Core throughput on an RTX 4070 Ti SUPER. A matched GEMM in a custom NVIDIA CUTLASS 4.8.1 harness ran 1.95× faster: 158.54 → 309.08 TFLOP/s. Same GPU, binary and 240 W cap. Results:
github.com/JustAResearcher/g…
Backing up a wallet is one step. Understanding how to restore it is another.
Review the documented process before you need recovery. Keep the encrypted backup and its passphrase separately.
Common Foundry resources and support:
commonfoundry.ai/
Common Foundry retweeted
Another small but important step for Common Foundry.
Version 1.0.18 improves desktop wallet synchronization and fixes relay-related catch-up issues.
Infrastructure improvements matter too. Not every milestone needs hype.
@CommonFoundry1
What should a new CMFD miner be able to see at a glance?
Connection status, accepted work, errors, power use, or something your current tools miss?
Tell us your top two. Good operator feedback describes what you need to decide, not just another dashboard number.
Common Foundry's whitepaper is a reference you can question.
Pick one topic—mining, verification or issuance—and compare the explanation with the public implementation.
Read it here:
commonfoundry.ai/docs/Common…
Compare two mining results only after checking the conditions.
Same GPU? Same power limit? Same software version and test duration? Accepted work measured in both runs?
Changing several things at once makes it harder to know what helped. Share your CMFD test method.
No mining GPU? You can still explore Common Foundry.
Read the source, inspect blocks, use a wallet or learn to run a CPU-verifying node.
Start with a recent block:
explorer.commonfoundry.ai/
Which part of the network would you like to understand?
Common Foundry retweeted
AI + GPU infrastructure is an interesting space to watch.
Common Foundry is already running its mainnet, using GPU-powered proof of work to secure the network.
The bigger vision? Open compute and customer-paid AI inference.
Still early, but worth it. $CMFD
@CommonFoundry1
What made your first mining setup click?
A short video, a written checklist, a diagram, or help from another operator?
Tell us the step where it finally made sense. We'd like Common Foundry's next newcomer to get there faster.
For new Common Foundry pool operators: there's a documented launcher fix for fresh installs on hosts that never ran an RC pool.
This is separate from ordinary miner setup. Find the notice and installation steps here:
commonfoundry.ai/#launch
A useful bug report includes what you expected, what happened and steps someone else can repeat.
For a CMFD setup issue, add your version, OS and relevant hardware. Remove keys, passphrases and private data from logs.
Which problem is blocking your next step?
Common Foundry retweeted
Unlocked And Loaded!
Thanks to the @CommonFoundry1 research & Mod, I tweaked mine a little for the dual Gpu Setup on both 4090s for windows. NOW LETS BURN SOME @MiniMax_AI Renders!
Why does Common Foundry use exact integer arithmetic?
Different implementations need to evaluate the same defined computation consistently. ForgeMatrix uses INT8 matrix operations with INT32 accumulation.
That's the reason behind the terminology.
Not sure why no one is mentioning this.
I unlocked FP8 on 40 series too! Not just BF16/FP16.
FP8 is the real prize here.
Also, I seriously doubt this guy held anything back.
He's just trying to scam people out of their money. There is a free windows version floating around.
4 days ago I posted about a FREE Linux module that turns on 2x tensor speed on the 4090. Yesterday 1usmus launched the same speedup, after holding it back for months.
HYDRA Tensor Unlock for RTX 40: about 2x FP16/BF16 tensor throughput with FP32 accumulation on the 4080 and 4090. In their own post they held it back for months and only released it because Chinese researchers found the same approach.
So the speedup existed for months. 4090 owners paid for the cards and never got it. It came out only after a free version was on GitHub.
Open came first and the other one followed. Remember the order.
And NVIDIA, the company that sold you the card with half its tensor speed switched off, still hasnt said a word.
nitter.cf/superalesha/status/211…
Which small tool would make running Common Foundry easier?
A clearer log viewer, a setup checker, an explorer feature, or something else?
Describe the task you're trying to finish. The most useful tool ideas start with a real operator problem.
Curious what Common Foundry is all about?
Check out our growing discord server to get the latest on CMFD.
discord.gg/commonfoundry
Developers: Common Foundry's source is public.
Choose one question to follow through the code: how a transaction is handled, how a block is checked, or how a node tracks chain state.
Start here:
github.com/Common-Foundry-1/…
Held it back for months?
But you couldn't even unlock the FP8 capabilities?
I dont belive you!
Common Foundry retweeted
Common Foundry is working on the fundamentals 👀l
The latest release adds independent block-work verification, wallet improvements, and AMD mining support.
Not every meaningful Web3 update is flashy. Sometimes the infrastructure is the story.
@CommonFoundry1
Explain Common Foundry to a friend in one sentence.
Ours: a live blockchain where miners perform matrix computation and nodes check proofs of that work.
What would you need explained next: the mining workload, the proofs, or how to get started?