vision.understanding.chart-qa-mini
2 entries.
Pareto frontier computed on
throughput_tok_per_s (higher is better) vs.
ttft_p50_ms (lower is better).
Rows marked P are on the frontier.
2 of 2 matching
| Model | Engine | Hardware | Quant | TTFT P50 (ms) | TTFT P99 (ms) | Throughput (tok/s) | $/M tokens | J/token | Power avg (W) | Power peak (W) | WER mean | J / audio s | Envelope | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Qwen/Qwen2-VL-7B-Instruct | vllm unknown | 8x NVIDIA H100 80GB HBM3 | fp16 | 84.89 | — | — | — | — | — | — | — | — | JSON | |
| Qwen/Qwen2.5-VL-7B-Instruct | vllm unknown | 8x NVIDIA H100 80GB HBM3 | bf16 | 50.78 | — | — | — | 105 | 620 | 634 | — | — | JSON |