RTX PRO 6000 Blackwell Server Edition · 96 GB
Qwen3.8-Flash-Next-NVFP4-NVIDIA
Open a report for complete measurements.
- Task
- Text generation · Text → Text
- Workload
- 8K → 2K tokens
- Concurrency
- 1 request
- Format · Engine
- NVFP4 · strata
- Unit
- tok/s
- Mean throughput
- 151tok/s
- Observed GPU occupancy
- 71.2 GiB
- First token
- 1.1 s
- Reports combined
- 1
Launch this model
This engine does not yet have an executable serving recipe.
Individual tests
Text → Text · Text generation · NVFP4 · strata · 8192in-2048out · tok/s
Sortable table
Uncached prefill is unavailable when prompts reuse cache or reliable phase timings are missing. Open a report for its recorded phase timings and cache counts.
| 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 |
|---|---|---|---|---|---|---|---|---|---|---|
| 10/14/2026, 10:49:01 AM | 151.39 tok/s | 1 | 15.457 | 1,140 | 71.22 | 292.25 | 165.23 | 7,274.88 | Parameters ↗ | 60a45fd1 ↗ |
Recorded test parameters
Configuration 1 · Parameters
- model
- Qwen3.8-Flash-Next-NVFP4-NVIDIA
- engine
- strata
- quant
- NVFP4
- method
- wbench-fixed-http-v1
- task
- llm
- dataset
- synthetic-tokenizer-v1:repeats=3
- context
- 8192in-2048out
- input_tokens
- 8192
- output_tokens
- 2048
- duration
- 3600
- concurrency
- 1
- unit
- tok/s
- software
- 296b59d2f73c8f04a805df29c2fa97655adace78
- engine_provenance
- { "config_sha256": "cc2e37629fd0805f36b576208d7e567c577e9524fa9a1fdf280dc45652211957", "kernel_settings": { "STRATA_PREFILL_NVFP4": "w4a4", "STRATA_PREFILL_X2_MIN_K": null, "STRATA_ROUTE_TAIL_SKIP": null }, "revision": "296b59d2f73c8f04a805df29c2fa97655adace78" }
- kernel_settings
- { "STRATA_PREFILL_NVFP4": "w4a4", "STRATA_PREFILL_X2_MIN_K": null, "STRATA_ROUTE_TAIL_SKIP": null }
- precision
- —
- resolution
- —
- performance_task
- —
- performance_scope
- —
- batch_size
- —
- dimensions
- —
- weight_quantization
- —
- max_sequence_length
- —
- model_scope
- —
- performance_dataset
- —
- workload_mode
- —
- graph_mode
- —
- model_revision
- —
- client_version
- 1.1.5