Upload a tree-based model. We compile it to C99 and serve it in an isolated container. 50µs inference. No Python on the hot path.
Works with your stack
~50 µs
Median latency
1.38M
Rows/sec throughput
<2 ms
P99 under load
0 ms
Cold start
# upload → compile → serve in seconds
$ timber upload fraud-detector.json
✓ Parsed 200 trees · 50 features
✓ Compiled to C99 (6 optimisation passes)
✓ SHA-256: 8f3a…c2d1
$ timber serve fraud-detector
● Listening on http://localhost:11434
inference: ~120 µs/row · 625K rows/sec
Everything you need to deploy tree-based models in production, without the Python overhead.
Models are compiled to native C99 at deploy time. No Python runtime, no GIL, no garbage collector in the hot path.
Single-row predictions in ~50 microseconds. Batch 10K rows in under 8ms. Consistent, predictable latency.
Each deployment runs in its own container with dedicated resources. No noisy neighbors. Auto-scaling built in.
Every compilation is SHA-256 hashed. Full audit trail. MISRA C-compliant generated code for regulated industries.
Supported frameworks
Single-row inference, 50-tree XGBoost model.
Upload your first model. See the difference in seconds.
Get started — it's free