Skip to content

Blazil — Open-Core Financial and AI Infrastructure

0TPS

10× Visa peak · fault-tolerant · failover tested live. AI-ready transport and verified distributed inference.

✓ VSR Live Failover Tested5 datasets · Tract ONNX · Qwen2.5-7B distributed pipeline verified

Blazil v0.3 was benchmarked on April 19, 2026 on an AWS i4i.4xlarge with 4 shards committing into a single 3-replica TigerBeetle VSR cluster. One replica was killed at t=80s — the cluster recovered in 37s with zero rejected events across 12,421,068 events. The same codebase now powers five production-grade dataset types, Tract ONNX inference, and a verified Qwen2.5-7B distributed pipeline. Real disk I/O, real network, real failover, and now a real AI infrastructure path on top of the same transport discipline.

0:00 / 0:00
10×above Visa peak · fault-tolerant
234KTPS · VSR · failover tested
$1,077/mo24/7 production cost (on-demand)
5production-grade dataset types

Searching for Blazil? This is the official Blazil software website from Kolerr Lab Inc. Read the brand overview.

Production Benchmarks · v0.3 · April 19 2026

233K TPS. Zero errors. Live failover tested.

Blazil v0.3 was benchmarked on AWS i4i.4xlarge with 4 shards committing to a 3-replica TigerBeetle VSR cluster. One replica was killed at t=80s — the cluster recovered in 37 seconds with zero rejected events. This is our primary production-grade claim: fault-tolerant by design, failover live-tested.

233,894
TPS Peak Throughput

Avg 180,500 TPS · 12,421,068 events processed · 0.000% error rate · VSR fault-tolerant consensus

3.5×
Lower Hourly Cost

$1.496/hr on i4i.4xlarge vs $5.29/hr TigerBeetle reference hardware — same VSR class, lower cost envelope

37s
Failover Recovery Time

Killed replica at t=80s during live benchmark · cluster recovered with zero rejected events · real production test

How Blazil compares to industry leaders

vs Industry

Published peaks for competitors · Blazil v0.3 (233K TPS) is our primary production claim

System
TPS
Cost / Type
Notes
Blazil v0.3 · AWS i4i · VSR Peak
233,894
AWS i4i.4xlarge
VSR fault-tolerant · 4-shard · failover tested · April 19 2026
Blazil v0.2 · Sharded
436,351
$252/month DO
Max throughput · 0% error · no cross-node consensus
Blazil v0.2 · VSR
130,998
$252/month DO
Fault-tolerant · 2/3 quorum · 0% error
Visa
~24,000
Proprietary
Published peak throughput
Coinbase (est.)
~10,000
Proprietary
Estimated peak
Mastercard
~5,000
Proprietary
Published peak throughput
Stripe (est.)
~5,000
Proprietary
Estimated peak
Mojaloop
~1,000
OSS
Open-source payment ledger baseline
SWIFT
~hundreds/day
Closed
Legacy settlement network

Why this matters: Blazil achieves 9.7× Visa's published peak (24K TPS) and 46× Stripe's estimated throughput (~5K TPS) on cost-effective hardware. Our v0.3 benchmark ran for 120 seconds with live VSR failover testing — significantly more rigorous than typical industry reports.

Cost profile against TigerBeetle reference hardware

TigerBeetle (Published Benchmark)

$5.29/hr

  • • Published TigerBeetle benchmark reference
  • • i8g.16xlarge class hardware
  • • ~38 second benchmark duration
  • • No live failover test published

Blazil v0.3 (AWS i4i.4xlarge)

$1.496/hr

  • • 1× AWS i4i.4xlarge instance
  • • 16 vCPU (Intel Xeon Platinum 8375C)
  • • $1,077/month at 24/7 utilization
  • • 120 second sustained benchmark
  • • Live VSR failover at t=80s (37s recovery)

3.5× lower hourly cost while running 3× longer with live fault tolerance testing. On-demand pricing for ap-southeast-1 region.

Architecture

From client to committed ledger without a single unnecessary copy.

gRPC streaming enters Go services, crosses into the Rust engine over TCP + MessagePack, lands on a lock-free LMAX Disruptor, and commits to TigerBeetle through VSR with O_DIRECT storage semantics. The same transport discipline now also underpins priority routing, cross-shard 2PC, and distributed AI inference.

ClientgRPC StreamGo Services256 in-flightzero RTTRust EngineLMAX Disruptor84ns P99TigerBeetleVSR · 3-node~1.6ms/roundLedgerio_uring · ACIDACIDgRPC streamTCP / io_uringBatch 100×VSR consensus

01

gRPC Bidirectional Streaming

Persistent connections with 256 in-flight requests per stream eliminate TCP handshake overhead on every transaction. The channel stays open; only the data moves.

02

TCP + MessagePack Handoff

Go services forward validated traffic into the Rust engine over a compact framed transport so the control plane stays explicit and the hot path stays lean.

03

LMAX Disruptor Ring Buffer

A single-producer lock-free ring buffer processes events at 84ns P99 latency — faster than a CPU cache miss. No locks means no contention, and no contention means linear scaling.

04

Cross-Shard 2PC

TigerBeetle pending, post, and void flows enable atomic reserve-and-commit behavior across shards instead of leaving distributed transfer correctness to application code.

05

Priority Routing

Independent Aeron streams let critical events target <1ms latency while high and normal traffic keep their own backpressure and fairness guarantees.

06

TigerBeetle VSR + io_uring

Viewstamped Replication across three nodes provides fault tolerance while io_uring keeps the storage path tight enough for both fintech and AI workloads to share the same operating model.

Full Stack

Layer
Technology
Purpose
Engine
Rust + LMAX Disruptor
Lock-free ring buffer · 262K capacity/shard · 42ns P99
Services
Go + gRPC streaming
Persistent streams · 256 in-flight window · zero RTT ingress
Transport
TCP + MessagePack · io_uring · Aeron IPC
1.2M TPS local · zero-copy IPC · sub-ms hot path
Ledger
TigerBeetle 0.16.78
VSR consensus · O_DIRECT disk writes · ACID
Pipeline
2 shards/node · 131K in-flight
Horizontal scaling · 97.7% efficiency at 2 shards
Cross-Shard 2PC
TigerBeetle pending/post/void
Atomic cross-shard transfers with reserve, commit, and abort paths
Priority Routing
Multi-stream Aeron
Critical <1ms · High <5ms · Normal <50ms · independent backpressure
Replication
VSR · quorum 2/3
Survives 1-node failure · no split-brain
AI / ML
Tract ONNX · 5 datasets · Qwen2.5-7B
Pure Rust inference · distributed LLM pipeline · dataset-agnostic transport
Infra
Docker + Ansible · Kubernetes
Reproducible clusters · ingress hardening · multi-environment ops
Observability
Prometheus + Grafana + OTel
Real-time metrics · distributed tracing
Security
Vault + Keycloak + OPA + cert-manager
Secrets · auth · policy · mTLS auto-rotation
Supply Chain
Syft SBOM + Cosign
Keyless image signing · provenance attestations in CI

AI Infrastructure

The same zero-copy discipline now powers datasets, inference, and distributed LLM serving.

Blazil is no longer just a high-throughput ledger engine. It now extends the same transport, observability, and operational model into AI workloads: Tract ONNX inference, io_uring data loading, five production-grade dataset types, and a verified Qwen2.5-7B distributed pipeline.

Pure Rust Inference

Tract ONNX inference and io_uring data loading remove Python and GPU runtime assumptions from the serving path.

Dataset-Agnostic Transport

All workloads flow through the same Sample<Vec<u8>> pipeline, so text, time-series, audio, and vision reuse the proven transport layer.

Distributed LLM Pipeline

Qwen2.5-7B is already running through a 3-stage Aeron IPC pipeline with token feedback, KV cache continuity, and multi-token generation.

Operator-Ready Foundations

Security, observability, and supply-chain controls are shared across fintech and AI workloads instead of being bolted on later.

Dataset Coverage

Dataset
Use Cases
Format
Status
Text / NLP
Sentiment, embeddings, semantic search
CSV, directory
7 tests
Time Series
Stock prediction, forecasting, sensor data
CSV with windowing
4 tests
Features
Fraud, anomaly, intrusion detection
CSV with normalization
6 tests
Audio
Voice commands, speaker ID, audio events
WAV
2 tests
Object Detection
Document verification, KYC, product detection
YOLO
2 tests

AI Metrics

Inference RPS

1,500–2,000

AWS i4i.4xlarge

Tract ONNX, CPU-only estimate pending production benchmark

Cost per RPS

$0.54–0.72/RPS/mo

AWS i4i.4xlarge

Comparable small-scale efficiency without GPU fleet overhead

Verified LLM run

32 tokens in 19.7s

Apple M4 CPU

Qwen2.5-7B-Instruct on distributed 3-stage pipeline

Why this matters

The README now positions Blazil as financial and AI infrastructure. The site needs to show that the AI side is already concrete: datasets are implemented, inference plumbing exists, and the distributed LLM path is verified rather than hypothetical.

Licensing

Open-core with a clear conversion path.

Blazil is source-available under Business Source License 1.1. Non-commercial use and research are free without restriction. Every release converts automatically to Apache 2.0 after four years. Production deployments require a commercial license.

BSL 1.1

Open Source

Free

forever

  • Full source access under BSL 1.1
  • Free for non-commercial use and research
  • Self-hosted evaluation with no time limit
  • Community support through GitHub Issues
  • Converts to Apache 2.0 — no action required
View on GitHub
Production

Commercial

Contact

for pricing

  • Production deployment rights across all markets
  • Commercial use license with legal clarity
  • Priority support with an SLA guarantee
  • Architecture review with Kolerr Lab Inc engineers
  • Enterprise compliance and audit package
Talk to the Architect

BSL 1.1 converts to Apache 2.0

Automatically, four years after each release date

Roadmap

Fintech scale, AI inference, and operating maturity now move on one roadmap.

v0.1 delivered 62,770 TPS on a 3-node DO cluster. v0.2 achieved 436K TPS sharded and 131K TPS VSR. v0.3 shipped April 19 2026 on AWS i4i.4xlarge — 233,894 TPS with live VSR failover testing. v0.3.1 integrated AI inference with Tract ONNX. v0.3.2 added multi-stream priority routing with <1ms critical latency. v0.3.3 hardened the platform with 2PC, mTLS, signed artifacts, and operator runbooks. v0.5 AI LLM verified distributed Qwen2.5-7B generation, and v0.5 AI Production now points toward large-model serving.

v0.1✓ Done62,770 TPS · DO cluster · gRPC
  • Core Rust engine with LMAX Disruptor ring buffer
  • TigerBeetle VSR consensus across three nodes
  • gRPC + Tokio UDP transport · 256 in-flight window
  • 3-node DigitalOcean cluster · $252/month · 0% error rate
v0.2✓ Done1.2M TPS local · 436K TPS sharded · 131K TPS VSR
  • Aeron IPC transport — 1,203,108 TPS peak on MacBook Air M4
  • io_uring disk writes · sharded TigerBeetle E2E integration
  • 2 shards per node · 436,351 TPS aggregate (3-node sharded)
  • 130,998 TPS with full VSR consensus · 2/3 quorum · 0% error
  • DO cluster benchmark completed April 13 2026 · SGP1
v0.3✓ Done233,894 TPS peak · AWS i4i · VSR failover tested
  • Production-grade single-shard with live VSR failover test
  • AWS i4i.4xlarge · Intel Xeon Platinum 8375C · 16 vCPU · 128 GiB · 1.9TB NVMe
  • 4 shards × dedicated TigerBeetle client · 3-node VSR cluster (loopback)
  • 233,894 TPS peak · 180,500 TPS avg · 12,421,068 events · 0% error
  • VSR failover tested: 1 replica killed at t=80s → recovered in 37s · bench continued
  • AWS Singapore · April 19 2026
v0.3 — AWS i4i.4xlarge · 233,894 TPS peak · VSR failover recovery tested · 12,421,068 events · 0% error · April 19 2026
v0.3.1 AI🔨 Implemented1,500–2,000 RPS estimate · AI inference pipeline
  • 5 production-grade datasets implemented
  • Tract ONNX runtime integration for AI inference
  • io_uring dataloader for high-throughput model serving
  • 2,291 LOC · 57 tests passing · CI 100% green
  • AI inference pipeline implemented · production benchmark pending
v0.3.2 Priority✓ DoneSame TPS · <1ms critical latency
  • Multi-stream priority routing (Critical/High/Normal)
  • Critical requests bypass queue with <1ms latency guarantee
  • 429 tests passing · 0 Clippy warnings
  • Production-ready priority scheduler deployed
v0.3.3 Hardening✓ DoneSame TPS · 2PC · mTLS · signed supply chain
  • Cross-shard 2PC via TigerBeetle pending/post/void flow
  • Kubernetes ingress + cert-manager mTLS automation
  • Prometheus PVC persistence and operational hardening
  • Syft SBOM + Cosign keyless signing in CI
  • 3 ADRs and 8 runbooks published for operators
v0.4 Fintech Scale🔮 Future1M+ TPS target · 4× i8g.16xlarge Graviton 4
  • 4× AWS i8g.16xlarge instances (Graviton 4, 64 vCPU each)
  • Sharded VSR cluster with horizontal scaling
  • Production benchmark pending · target 1M+ sustained TPS
  • Multi-region replication architecture
Target: 2027 — bare-metal NVMe Gen4 · XDP ingress · estimated 5–10M TPS sharded · 1–2M TPS VSR
v0.5 AI LLM✓ Verified32 tokens in 19.7s · distributed Qwen2.5-7B
  • Qwen2.5-7B-Instruct distributed 3-stage inference pipeline
  • Stage orchestration across Aeron IPC streams 1001/2001/2002/1002/1003
  • Language Drift issue fixed and English generation verified
  • KV cache preserved across decode steps with correct position propagation
  • Production-ready multi-token generation on CPU-only Apple M4
Qwen2.5-7B-Instruct · 3-stage distributed pipeline · 32 tokens in 19.7s on Apple M4 CPU · multi-token generation verified
v0.5 AI Production🔮 FutureTBD RPS · AI inference production benchmark
  • Cortex v1 on ClarkenAI 70B plus Blazil Super Engine
  • Cloud cost validation against commercial inference APIs
  • Ankatos runtime integration and shared transport layer
  • Production benchmark pending for large-model serving

The source is open and the benchmarks are reproducible.

Clone the repository, run the benchmark suite, and verify every number yourself.

View on GitHub →

Enterprise

Talk to the Architect.

If you are evaluating payment ledger infrastructure, planning a core banking modernization, or building a low-latency AI serving stack on the same operational substrate, the right conversation is with the engineer who designed and built the system.

  • 233,894 TPS · 1 VSR cluster · 4 shards · 12,421,068 events · 0% error
  • 5 production-grade dataset types · Tract ONNX · distributed Qwen2.5-7B verified
  • Cross-shard 2PC · mTLS hardening · SBOM + Cosign supply-chain controls

Direct contact

ricky@kolerr.com

Ricky Anh Nguyen · Founder & Principal Architect

lab.kolerr@kolerr.com

General · licensing · partnerships

Send a message →

No sales funnel. No SDR. A direct line to the engineer who built the system.