WeVisOne-VL-2B
Run this model
Choose your operating system and enter a model repository. Launch support is checked separately from performance results.
Test conditions
- Task
- Text generation · Text → Text
- Workload
- 64K → 2K tokens · Prefix cache reuse
- Concurrency
- 7 concurrent requests
- Format · Engine
- BF16 · vllm · vLLM 0.28.0
- Unit
- tok/s
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.
Protocol details
wbench-search-http-v1 · migration-analysis-v1:sha256=68590c248e43f32c04dfd8062464fd1e4856917795fe307225e5c6112a54fe94:cache=prefix-reuse:repeats=3 · 65536in-2048out
GPUs on this test
Only one GPU configuration has matching measurements; a cross-hardware comparison is not yet available.
- Mean throughput
- 340tok/s
- Observed GPU occupancy
- 85.3GiB
- First token
- 227 ms
- Reports combined
- 1
Sortable table
| Hardware | Mean throughput (tok/s) | P95 (s) | TTFT (ms) | Observed occupancy (GiB) | GPU power (W) | Throughput / W | VRAM per GPU (GB) | Reports combined |
|---|---|---|---|---|---|---|---|---|
| #1RTX PRO 6000 Blackwell Server Edition · 96 GBRuns, parameters and setup ↗ | 340.1 | 42.269 | 227.1 | 85.25 | 496.1 | 0.69 | 96 | 1 |
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.
How results are grouped
Results merge successful runs of the same model, precision and workload. CPU thread counts and CUDA wheel builds may differ; actual PyTorch builds are shown. Other recorded protocol settings remain separate.
Updated 11/5/2026, 9:56:22 PM