Estimate a local configuration
Use the calculator for planning, then follow reviewed result links when an exact artifact, runtime and hardware observation exists. Query-state URLs are useful to share but are not indexed.
01
Estimator formula v0.1Check a configuration
OBSERVED ATTEMPT
Allocation loaded; short request completed.
Qwen3.8-27B · Q4_K_M · 32K allocated context
Reviewed receipt: 17.7 GiB sampled peak and 47.7 tok/s median generation for 512-input/128-output requests; this is not a full-context prompt test.
ESTIMATED PEAK RANGE21.4–22.3GB · 24 GB available
- Weights
- 16.7 GB
- KV cache
- 2.0 GB
- Runtime
- 1.3 GB–2.2 GB
- Reserve
- 1.4 GB
CONSERVATIVE HEADROOM1.7 GB
Important: observed labels apply only when this exact model, hardware, quantization and context matches a reviewed receipt. Every other selection remains a transparent estimate.