Skip to content
m.recipes
Find a configuration
Sign in
179 GB · 13 reports

B200 · 179 GB

Qualified results first; original reports and full tables stay below.
Reset

Decision · Qualified results

Speeds compare only within one exact test. Recipe availability is checked on each report against the published recipe executor.

No qualified results yet · Decision · B200 · 179 GB

No reports for this task have been recorded here. This does not show that the model or GPU cannot run it.

Check model launch supportMeasured alternatives for this taskTest your own GPU

Measured alternatives on other GPUs

Measured on different GPUs with the same or smaller listed capacity. These are references for choosing hardware, not performance or compatibility evidence for your selected GPU.

  1. StartLux-Decision-v1-0.8B

    startlux-models · 2 tested configurations · 1 GPU

    • RTX PRO 6000 Blackwell Server Edition · 96 GBbf16 · Text → Structured data · typed-invoices-v1 · Test duration 6 s
      Throughput · Batch 1
      50.3decisions/sec
      Observed GPU occupancy
      3.2GiB
      P95 latency
      20 ms
      Use this recipe · Batch 1 ↗Evidence report and run availability ↗Same test on other GPUs
      Test details

      Occupancy includes engine buffers and reserved KV cache. It is not the minimum VRAM required by the model.

      Reports combined counts reports, not inference requests. Request successes and failures are listed in each report.

      Engine
      startlux-native · PyTorch 2.11.0+cu130
      Protocol
      native-forward-v1
      Dataset
      typed-invoices-v1
      Workload
      decision
      Batch sizeMean throughput (decisions/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
      B150.2520 ms—3.17161.31df141700 ↗
    • 1 other test configurations on this GPU
      • bf16 · Text → Structured data · typed-invoices-v1 · Test duration 6 s
        Throughput · Batch 1
        50.3decisions/sec
        Observed GPU occupancy
        2.3GiB
        P95 latency
        20 ms
        Use this recipe · Batch 1 ↗Evidence report and run availability ↗Same test on other GPUs
        Test details

        Occupancy includes engine buffers and reserved KV cache. It is not the minimum VRAM required by the model.

        Reports combined counts reports, not inference requests. Request successes and failures are listed in each report.

        Engine
        startlux-native · PyTorch 2.11.0+cu130
        Protocol
        native-forward-v1
        Dataset
        typed-invoices-v1
        Workload
        decision
        Batch sizeMean throughput (decisions/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
        B150.2820 ms—2.2916518c1985ea ↗

  2. Intern-Decision-0.8B

    internlm · 4 tested configurations · 1 GPU

    • RTX PRO 6000 Blackwell Server Edition · 96 GBbf16 · Text → Structured data · typed-invoices-v1 · Test duration 6 s
      Throughput · Batch 1
      50.8decisions/sec
      Best measured · Batch 17
      347decisions/sec
      Observed GPU occupancy
      2.4GiB
      P95 latency
      20 ms
      Use this recipe · Batch 17 ↗Evidence report and run availability ↗Same test on other GPUs
      Test details · 2 batch sizes

      Occupancy includes engine buffers and reserved KV cache. It is not the minimum VRAM required by the model.

      Reports combined counts reports, not inference requests. Request successes and failures are listed in each report.

      Engine
      intern-decision-native · PyTorch 2.11.0+cu130
      Protocol
      native-forward-v1
      Dataset
      typed-invoices-v1
      Workload
      decision
      Batch sizeMean throughput (decisions/sec)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
      B150.8320 ms—2.36169218b06f63 ↗
      B17346.7250 ms—3.0737816ccb367c ↗
    • 3 other test configurations on this GPU

Occupancy includes engine buffers and reserved KV cache. It is not the minimum VRAM required by the model.

Original reports

Every report for this task, including quality, diagnostic and legacy runs that do not enter comparisons.
Original reports · 0 rows
ModelTest taskFormatEngineWorkloadProtocolQuality scoreTest date
No matching results

Running benchmarks

0Updates automatically

No benchmarks are currently reported as running.

Methodology

Average of error-free runs for the selected recorded configuration. Missing methods and fallback runs are not ranked. Performance index = average / fastest matching hardware × 100. Value index = performance per purchase cost / best comparable value × 100. Quality is separate by dataset and protocol. Prices are dated seller listings, not completed transactions or market averages.

Updated 11/5/2026, 11:01:57 PM