vGPU-32GB · 32 GB
clef-flash
Open a report for complete measurements.
- Task
- Decision · Text → Structured data
- Workload
- Text → Structured data · typed-invoices-v1 · Test duration 6 s
- Batch size
- Batch 1
- Format · Engine
- bf16 · clef-native · PyTorch 2.13.0+cu130
- Unit
- decisions/sec
- Mean throughput
- 10.6decisions/sec
- Observed GPU occupancy
- 18.2 GiB
- P95 latency
- 99 ms
- Reports combined
- 2
Launch this model
Open the decision recipe to start its API or repeat the measured batch.
Use this recipeIndividual tests
Text → Structured data · Decision · bf16 · clef-native · decision · decisions/sec
Sortable table
| Test date | Throughput | Concurrency / batch | P95 (s) | TTFT (ms) | Observed occupancy (GiB) | GPU power (W) | Decode (tok/s) | Uncached prefill (tok/s) | Parameters | View report |
|---|---|---|---|---|---|---|---|---|---|---|
| 10/7/2026, 11:11:06 AM | 10.48 decisions/sec | 1 | 0.103 | — | 18.17 | 203.91 | — | Uncached prefill unavailableView report | Parameters ↗ | c015746c ↗ |
| 10/7/2026, 12:51:07 PM | 10.65 decisions/sec | 1 | 0.095 | — | 18.17 | 208.38 | — | Uncached prefill unavailableView report | Parameters ↗ | 63f44036 ↗ |
Recorded test parameters
Configuration 1 · Parameters
- model
- ms:Cloudflare/clef-flash
- engine
- clef-native
- quant
- bf16
- method
- native-forward-v1
- task
- decision
- dataset
- typed-invoices-v1
- context
- decision
- input_tokens
- 0
- output_tokens
- 0
- duration
- 6
- concurrency
- 1
- unit
- decisions/sec
- software
- { "torch": "2.13.0+cu130", "transformers": "5.19.0", "sentence-transformers": "6.1.0", "ctranslate2": "4.8.2", "faster-whisper": "1.2.1" }
- engine_provenance
- —
- kernel_settings
- —
- precision
- bf16
- resolution
- —
- performance_task
- —
- performance_scope
- —
- batch_size
- —
- dimensions
- —
- weight_quantization
- —
- max_sequence_length
- —
- model_scope
- typed-decision-head
- performance_dataset
- —
- workload_mode
- —
- graph_mode
- —
- model_revision
- —
- client_version
- python-native-bench-1.1.3