Skip to content
m.recipes
Find a configuration
Sign in
1 models with qualified results

Models

Measured configurations by model. Open a model to compare GPUs on one exact test.

Get your startup command

Choose your operating system and enter a model repository. Launch support is checked separately from performance results.

Reset

Text generation · RTX 5090 · 32 GB

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

  1. Qwen3.8-27B-NVFP4

    RadixArk · 2 tested configurations

    • NVFP4 · 8K → 2K tokens
      Output throughput · includes prefill · 1 request
      70.8tok/s
      Observed GPU occupancy
      27.3GiB
      First token
      633 ms
      Use this recipe · 1 request ↗Evidence report and run availability ↗Same test on other GPUs
      Test details

      Total output tokens divided by the full request window, including prefill and queueing.

      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
      vllm
      Protocol
      wbench-fixed-http-v1
      Dataset
      synthetic-tokenizer-v1:repeats=2
      Workload
      8192in-2048out
      ConcurrencyMean throughput (tok/s)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
      C170.8229.01 s633 ms27.29405.51bad294c0 ↗
    • 1 other test configurations on this GPU
      • NVFP4 · 32K → 2K tokens
        Output throughput · includes prefill · 1 request
        62.5tok/s
        Observed GPU occupancy
        27.3GiB
        First token
        3.6 s
        Use this recipe · 1 request ↗Evidence report and run availability ↗Same test on other GPUs
        Test details

        Total output tokens divided by the full request window, including prefill and queueing.

        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
        vllm
        Protocol
        wbench-fixed-http-v1
        Dataset
        synthetic-tokenizer-v1:repeats=2
        Workload
        32768in-2048out
        ConcurrencyMean throughput (tok/s)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
        C162.4832.79 s3.6 s27.29433.31746bbc39 ↗
Sortable tables by exact test condition · 2 rows
Text generation · 8K → 2K tokens · 1 request · tok/s · 1 rows
ModelHardwareFormatEngineMean throughput (tok/s)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
Qwen3.8-27B-NVFP4RTX 5090 · 32 GBNVFP4vllm70.8229.01 s633 ms27.29405.51bad294c0 ↗
Text generation · 32K → 2K tokens · 1 request · tok/s · 1 rows
ModelHardwareFormatEngineMean throughput (tok/s)P95TTFTObserved occupancy (GiB)GPU power (W)Reports combinedView report
Qwen3.8-27B-NVFP4RTX 5090 · 32 GBNVFP4vllm62.4832.79 s3.6 s27.29433.31746bbc39 ↗
Models with reports but no qualified results · 15

Their original reports remain available on each model page. They did not qualify for comparison; each report states why.

Models with reports but no qualified results · 15 rows
ModelTest task
Hunyuan-MT2-1.8B-FP8Tencent-Hunyuan/Hy-MT2-1.8B-FP8Text generation
Hunyuan-MT2-7B-FP8Tencent-Hunyuan/Hy-MT2-7B-FP8Text generation
MiniCPM-V-4.7-35B-A3B-NVFP4sambit9238/MiniCPM-V-4.7-35B-A3B-NVFP4Text generation
Qwen3-0.6B-FP8Qwen/Qwen3-0.6B-FP8Text generation
Qwen3-0.6B-Q8Qwen/Qwen3-0.6B-GGUF/Qwen3-0.6B-Q8_0.ggufText generation
Qwen3-1.7B-FP8Qwen/Qwen3-1.7B-FP8Text generation
Qwen3-4B-FP8Qwen/Qwen3-4B-FP8Text generation
Qwen3-8B-FP8Qwen/Qwen3-8B-FP8Text generation
Qwen3-8B-NVFP4RedHatAI/Qwen3-8B-NVFP4Text generation
Qwen3-14B-FP8Qwen/Qwen3-14B-FP8Text generation
Qwen3-14B-NVFP4RedHatAI/Qwen3-14B-NVFP4Text generation
Qwen3-VL-2B-Instruct-FP8Qwen/Qwen3-VL-2B-Instruct-FP8Text generation
Qwen3-VL-4B-Instruct-FP8Qwen/Qwen3-VL-4B-Instruct-FP8Text generation
Qwen3-VL-8B-Instruct-FP8Qwen/Qwen3-VL-8B-Instruct-FP8Text generation
qwen3:0.6bqwen3:0.6bText generation