AtacamaODR Apple Silicon
Download .dmg
Apple Silicon Continuous Batching Engine Live

The Sovereign Edge Proxy That Slashes Cloud LLM Bills by 80%

AtacamaODR intercepts developer CLI & agent traffic (claude, cursor, gemini). It compresses conversational bloat with proprietary context compaction and executes code turns locally on your Mac's Metal GPU—mechanically quarantining sensitive IP.

85–92%
Adaptive Token Compaction
2,968 tok/s
Peak Concurrency Throughput
31.8 ms
Interactive Turnaround Replay
0 Egress
Multi-Pattern Secret Quarantine
Explore full 500+ workload technical benchmark report →

Enterprise Token Bill Shock Calculator

See how much AtacamaODR saves your team every month in Claude & Gemini API credits.

Active Developers / AI Agents: 10 developers
Average Daily Turns Per Dev: 80 turns/day
Cloud Frontier Model: Claude 3.5 Sonnet
Standard pricing: $3.00/M input, $15.00/M output. Unoptimized sessions re-transmit 15K–30K tokens of unchanged code files every turn.
Estimated Monthly Cloud Spend
$4,320 / mo
With AtacamaODR On-Device Optimization
$864 / mo
Saves $3,456 / month (80% Reduction)
EMPIRICAL EVALUATION SUITE • 7 DEDICATED TRACKS

Verified Enterprise Benchmarks

Every metric is measured directly on Apple Silicon under production test conditions. Evaluated on AtacamaODR 14B (100% Pure Local) with larger model sweeps planned. Zero synthetic estimations.

TRACK 01 Explore →

Multi-Worker Concurrency

Sustained 16k stress test across 1 to 20 workers. Eliminates queue timeouts and VRAM exhaustion.

Peak: 2,968 tok/s • 0.06s TTFT
TRACK 02 Explore →

Cost Economics (100 Tasks)

100 real-world engineering tasks and 25 session replays benchmarked against Claude 3.5 Sonnet.

60.8% Savings • 100% Replay Local
TRACK 03 Explore →

SWE-bench Verified

50 verified bug-fix tasks evaluating Pass@1 accuracy under 86.7% context compaction.

84.0% Pass@1 • -95.0% Cost/Issue
TRACK 04 Explore →

NIAH & RULER Heatmap

Variable tracking matrix across 8k to 64k tokens and 5 document depth tiers (10% to 90%).

100.0% Accuracy • 0% Dilution
TRACK 05 Explore →

OWASP 500 & powermetrics

500-sample credential quarantine ledger paired with Apple M5 Pro powermetrics kernel telemetry.

0 Leaks • 1.74 J/1k tok • 231mW Idle
TRACK 06 Explore →

Hardened Frontier Suites

RepoBench-P (cross-file repo), BAMBOO 64k (state tracking), Berkeley BFCL, and APPS code.

RepoBench 85% EM • BFCL 96.0%
TRACK 07 Explore →

AtacamaODR 14B (Pure Local)

HumanEval (82.3%), MBPP (81.5%), LCB (41.7%), GSM8K (88.5%), IFEval (80.7%) on Metal GPU ($0.00 cloud egress).

HumanEval: 82.3% • GSM8K: 88.5%

Dual-Plane Sovereign Routing Architecture

Never compromise between speed, air-gapped data security, and frontier reasoning capacity.

Plane 1: Local Sovereign Execution
Atacama Sovereign Engine (Hardware-Adaptive Qwen 2.5 Coder on Metal GPU)

Powered by state-of-the-art Qwen 2.5 Coder (4-bit native Apple Silicon Metal quantization). AtacamaODR's autonomous hardware profiler automatically selects the optimal parameter scale for your Mac's unified memory: 1.5B on 8GB Macs, 7B on 16GB Macs, 14B on 24–36GB M-series Pro chips, and 32B on 48GB–128GB+ Max/Ultra workstations. Resolves interactive code modifications, unit test authoring, and multi-file refactors directly on-device with zero cloud latency.

  • ✓ 70–120 tok/s native Metal throughput
  • ✓ Air-gapped on-device execution (zero egress on local turns)
  • ✓ Adaptive Context Compaction prunes 85–92% of redundant tokens
  • ✓ Resolves ~72% of pairing turns at $0.00 cloud spend
Plane 2: Frontier Cloud Escalation
Intelligent Predictive Gateway

When task complexity, cross-module refactors, or prompt lengths exceed optimal on-device thresholds, AtacamaODR's autonomous predictive governor seamlessly upshifts to Claude 3.5 Sonnet, Gemini 2.5 Pro, or your corporate AI gateway.

  • ✓ Up to 2,000,000 token context horizons
  • ✓ Pre-compacted payloads save 50%+ input cost
  • ✓ Zero manual model switching in developer CLI