DeAI Nation
Data sources
Projects / Darkbloom

About

Darkbloom

Darkbloom

API Offchain

An off-chain private-inference network built around Apple Silicon. This dashboard reports source-labelled application traffic, capacity, model pricing, and aggregate hardware trust signals. Its B200 Index uses only public attestation rows that identify both an Apple chip and its GPU-core configuration.

This page tracks Darkbloom private-inference traffic, model pricing, Apple Silicon capacity, and public hardware-attestation signals without treating incomplete attestations as fleet totals.

Latest included observation: 2026-10-30 UTC. Metric timestamps and coverage can differ by source.

darkbloom.dev/ Docs GitHub

Overview

B200 Index ? 22.34 ▼ 0.2% 7d
Throughput ? 2.43Btok/day ▲ 1.6% 7d
Community Score ? 20.53/ 100

Apple Silicon Capacity & Trust

Latest public aggregate snapshot; not GPU inventory or uptime
Active Providers1,119
Reported Capacity (tok/s)21,864.20
Network Utilization6.05%
Active / Queued Requests312 / 0
Model Capacity (tok/s)139,395.92
Cumulative Requests337,852,006
Cumulative Tokens1,048,355,690,974
24h Requests / Tokens4,021,212 / 0
Apple GPU Cores41,687
CPU Cores19,225
Unified RAM (GB)106,688.00
Memory Bandwidth (GB/s)577,827.00
Power Under Load (W)185,233.00
Hardware-attested Providers1,118
B200 Index (Attested Macs)22.343274
Theoretical Throughput (tok/day)2.43B
Secure Enclave Providers1,118
Code-attested Providers982

Darkbloom's aggregate Apple GPU-core total is not a B200 Index. Separately, public attestation rows that identify chip, GPU-core count, and per-Mac unified RAM are aggregated with the documented Apple Silicon coefficients. The theoretical throughput applies the same 70 GB reference workload used for other networks, so only Macs with at least 96 GB RAM contribute; raw B200 Index remains independent of this gate. This is attested-machine capacity only—not uptime, delivered capacity, or a conversion of RAM/aggregate core totals. Darkbloom source ↗

Inference

Socials