RandomX, rebuilt for GPUs.
Random-program mining is the idea Igneum borrowed. Here is what changed when it was rebuilt for graphics cards, and what RandomX’s seven years say and do not say about this chain. The same text as the litepaper’s section.
RandomX has kept chips off Monero since 2019 (approximate) by making the mining program random, so the hardware that runs it well is the hardware everyone already owns. The one chip announced against it, Bitmain’s Antminer X9 (pre-orders from 26 December 2025 at 1 MH/s and 2,472 W, about USD 5,600), was withdrawn in mid-May 2026 before any unit shipped; RandomX 2.0 shipped on 25 March 2026 (monero-project/monero issue 10270). Igneum takes the same principle to graphics cards and adds what RandomX never had.
| Property | RandomX, Monero | Igneum |
|---|---|---|
| Hardware it is built for | CPUs. GPUs run it badly on purpose | GPUs. Any card, any vendor. Bit-exact on Apple, NVIDIA and AMD, measured |
| Random program | Per hash, interpreted in a virtual machine | Per hour, compiled to native GPU code. Per hash, the 128 dataset addresses change with the nonce |
| Dataset | About 2 GB, the same size since 2019, approximate | 2 GB, growing (the proposed schedule, fixed at the testnet genesis: 2 GB, doubling at years 4, 12 and 28); a 4 GB card mines about four years, an 8 GB card about twelve, approximate |
| Light verification | 256 MB cache on a CPU, milliseconds | 256 MB cache on a CPU (512 MB from year 4), one warp under 10 ms, the gate. Measured 2.1 ms on one Apple M5 Max core for class v3 (3.4x class v2's 0.61 ms); a 2019-class core not yet |
| Changes over time | None. A fixed design, unchanged for seven years | A new program every hour, its memory pattern with it; era draws and reserved families on a schedule fixed at genesis. Nobody touches it |
| Seed grinding | Not applicable, the program comes from the hash input | Closed by a verifiable delay between seed and program |
| Useful work | None. Hashing only | Every NVIDIA card from 8 GB proves; 12 GB and up mine and prove; 24 GB on the stock server (eleven rented cards, RTX 3060 to RTX 5090, 6 October 2026); they sell proofs to other chains. AMD and Apple cards mine, and a prover for them lands when a zkVM ships one |
| Track record | About seven years without a shipped chip; the one announced, Bitmain’s Antminer X9, was withdrawn in May 2026 before launch | Zero years. Every number above is measured and logged with the commands that produced it. The specification, reference hash, test vectors and simulators are public now (git.igneum.network/igneum-network/spec). The node, the miner and the wallet follow to the same host as the repository is published |
Measured so far: the same hourly program, generated on an Apple M5 Max, compiled by Apple's Metal and NVIDIA's CUDA on an RTX 5090, produced identical hashes on both, 192 of 192 across two programs. On a 1 GB dataset the 5090 ran at about 228 million hashes a second and the Mac at about 45 million, both bound by random memory access rather than arithmetic. Those are prototype figures, not mining rates. The first prototype dataset was a closed-form function, and a miner could compute items instead of loading them: measured 111x faster that way on the Mac. The 256 MB cache construction replaced it on 3 October 2026. With the cache, computing items on the fly runs 4.8x slower than loading them, measured on the Mac, and the honest rate is unchanged on both vendors. Open: the same shortcut ratio on NVIDIA and on a discrete AMD card, and the time-memory trade-off between the two measured points. Inside the 5090's 96 MB cache the same program ran nearly six times faster, which is why the dataset starts at 2 GB and grows. On 4 October 2026 the live devnet crossed an hourly program change on all three vendors with no pause and no rejected block: a Mac at 26.7 million hashes a second, an RTX 5090 at 123 million and an integrated AMD chip at 2.7 million, every hash doing 128 distinct reads of the memory-hard dataset.