Hekate – A Zero-Copy ZK Engine Overcoming the Memory Wall
Most ZK proving systems are optimized for server-grade hardware with massive RAM. When scaling to industrial-sized traces (2^20+ rows), they often hit a "Memory Wall" where allocation and data movement become a larger bottleneck than the actual computation. I have been developing Hekate, a ZK engine written in Rust that utilizes a Zero-Copy streaming model and a hybrid tiled evaluator. To test its limits, I ran a head-to-head benchmark against Binius64 on an Apple M3 Max laptop using Keccak-256. The results highlight a significant architectural divergence: At 2^15 rows: Binius64 is faster…
What it does
In the maker’s words, at launch
Most ZK proving systems are optimized for server-grade hardware with massive RAM. When scaling to industrial-sized traces (2^20+ rows), they often hit a "Memory Wall" where allocation and data movement become a larger bottleneck than the actual computation. I have been developing Hekate, a ZK engine written in Rust that utilizes a Zero-Copy streaming model and a hybrid tiled evaluator. To test its limits, I ran a head-to-head benchmark against Binius64 on an Apple M3 Max laptop using Keccak-256. The results highlight a significant architectural divergence: At 2^15 rows: Binius64 is faster (147ms vs 202ms), but Hekate is already 10x more memory efficient (44MB vs ~400MB). At 2^20 rows: Binius64 hits 72GB of RAM usage, entering swap hell on a laptop. Hekate processes the same workload in 4.74s using just 1.4GB of RAM. At 2^24 rows (16.7M steps): Hekate finishes in 88s with a peak RAM of 21.5GB. Binius64 is unable to complete the task due to OOM/Swap on this hardware. The core difference is "Materialization vs. Streaming". While many engines materialize and copy massive polynomials in RAM during Sumcheck and PCS operations, Hekate streams them through the CPU cache in tiles. This shifts the unit economics of ZK proving from $2.00/hour high-memory cloud instances to $0.10/hour commodity hardware or local edge devices. I am looking for feedback from the community, especially those working on binary fields, GKR, and memory-constrained SNARK/STARK implementations.
Does the same job
all alternatives →- OSOpen-source engine running Gemma 4 26B in 2 GB RAM on any M-series MacJul 2026 · github.com · ▲919
Hi HN, I built a specialized inference engine for running 4-bit Gemma 4 26B-A4B-IT on any M-series Mac using about 2 GB of RAM. It is called TurboFieldfare and is written in Swift and Metal. I have always adored on-device AI. It feels like magic that you can run a powerful NN on your Mac or iPhone. So I wanted to push the limits a bit and run a model whose weights don’t fit in memory. The model’s 4-bit quantized weights occupy roughly 14 GB, which makes running it with conventional inference tools almost impossible on an 8 GB or even 16 GB Mac once the OS, applications, and KV cache are…
- ATA tiny LLM running at 21,000 tok/s on a $250 FPGA (Live Demo)27d ago · mikeayles.com · ▲79
A 3.16M-parameter INT4 transformer running entirely in the on-chip memory of a Xilinx Kria KV260. Zero DRAM in the token loop, 59,965 tok/s on the fabric, bit-exact. Chat with it live.
- IBI Built a Groth16 ZK-Proof Verifier from Scratch Using Rust2024 · github.com · ▲6
I've always been fascinated by cryptographic principles, so I decided to dive deep into zero-knowledge proofs and implement a Groth16 proof verifier entirely in Rust. This project validates cryptographic proofs and demonstrates how succinct, verifiable computations can be achieved. Using Rust's powerful libraries like arkworks, I implemented pairing checks, public input commitments, and proof validation logic while ensuring the code remains modular and efficient. I handled the complexities of affine group operations, scalar multiplications, and optimized public input verification to make…
MCP-stama – An ultra-fast Rust MCP server with no dependencies23d ago · github.com · ▲73An ultra-fast, single-binary MCP server written in Rust as a lightweight alternative to Node.js/Python. - StamManif/mcp-stama
Kern – container and resource runtime in a 1.5 MB binary, no daemon13d ago · github.com · ▲70A fast, rootless sandbox and virtual resource runtime for any workload, including untrusted and AI-generated code. Daemonless: a real, kernel-enforced container in ~3.5 ms from an OCI image, out of one static binary - getkern/kern
We Beat MLPerf: Modern Storage for KV Offload and LLM Training14h ago · theopenlake.com · ▲35High performance storage engine for efficient LLM inference and GPU Training.
More dev tools this month
the category →
Open-source GTM skills for technical founders
Dev tools · 29d ago · gtmcofounder.com
OpenTrailPaper is open-source bike computer firmware for the LilyGO T5S3 4.7" E-Paper PRO. It supports offline maps, GPX routes, FIT recording and Bluetooth sensors.
Dev tools · 2d ago · opentrailpaper.com
Launched alongside, January 2026
the whole month →- IN
Hey HN! I wanted to share something I built over the last few weeks: isometric.nyc is a massive isometric pixel art map of NYC, built with nano banana and coding agents. I didn't write a single line of code. Of course no-code doesn't mean no-engineering. This project took a lot more manual labor than I'd hoped! I wrote a deep dive on the workflow and some thoughts about the future of AI coding and creativity: http://cannoneyed.com/projects/isometric-nyc
AI · Jan 2026 · cannoneyed.com
Automatic AI-powered code reviews the moment you open a PR
Dev tools · Jan 2026 · kilo.ai
