# COSMOS Performance Profile

## Multi-Turn Chat Performance (5 turns)
| Turn | Prompt | Latency (s) | Peak RSS (MB) | Exit Code |
|------|--------|-------------|--------------|-----------|
| 1 | Hello Cosmos! How are you feeling right now? | 7.716 | 24.30 | 0 |
| 2 | Explain briefly CST phase attention | 5.057 | 24.41 | 0 |
| 3 | Summarize Hebbian plasticity learning rule | 5.858 | 24.56 | 0 |
| 4 | Write pseudocode for persistent memory update | 7.984 | 24.46 | 0 |
| 5 | Safety note about online plasticity | 2.916 | 24.42 | 0 |

**Observations:**
- Average latency: 5.9 s per response
- Memory usage stable: ~24–25 MB (CLI process peak)
- All requests completed successfully

## 20-Turn Continuous Chat (Context Persistence Test)
Testing Hebbian plasticity and context retention over extended conversation.

| Turn | Latency (s) | Output Chars |
|------|-------------|--------------|
| 1 | 2.083 | 19 | | 2 | 2.621 | 99 | | 3 | 2.617 | 90 | | 4 | 6.302 | 402 | | 5 | 7.565 | 595 | | 6 | 4.134 | 222 | | 7 | 3.106 | 129 | | 8 | 11.204 | 982 | | 9 | 5.459 | 358 | | 10 | 2.83 | 123 | | 11 | 5.496 | 311 | | 12 | 3.101 | 144 | | 13 | 17.624 | 1626 | | 14 | 10.17 | 793 | | 15 | 9.594 | 735 | | 16 | 6.993 | 505 | | 17 | 5.163 | 327 | | 18 | 5.46 | 378 | | 19 | 4.685 | 347 | | 20 | 4.405 | 278 |

**Observations:**
- Average latency across 20 turns: 6.031 s
- Total conversation time: 120.612 s
- No latency degradation observed over extended turns (indicates stable context handling)

## Concurrent Request Performance (3 parallel requests)
Testing throughput and concurrency on local machine.

| Request | Output Chars |
|---------|--------------|
| 1 | 62 | | 2 | 1385 | | 3 | 358 |

**Total time for 3 parallel requests:** 23.0749368 s

**Observations:**
- All 3 requests completed in parallel without errors
- Total time ~23.07s (faster than serial execution)

## System & Model Info
- Model: COSMOS (54D) Q4-quantized GGUF
- Local runtime: Ollama
- Machine: Windows (reported peak memory ~24–25 MB for ollama CLI process)
- Model size: 3.1 GB
- Quantization: Q4

## Recommendations
- Model is suitable for interactive local inference on CPU
- Memory footprint is minimal for the CLI process; GPU/host memory needs detailed profiling
- No performance degradation over 20+ turns suggests stable context and plasticity handling
- Concurrent request support confirmed on local machine

## Next Steps
- Test on Atomic AI platform (iOS/remote runtime)
- Profile GPU memory usage if available
- Test with longer context windows (8K+)
- Implement token-per-second (TPS) benchmarking