Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | Qwen3 VL 30B A3B Instruct | Llama 3.2 Instruct 90B (Vision) |
|---|---|---|
| Input ($/M tokens) | $0.2 | $0.72 |
| Output ($/M tokens) | $0.8 | $0.72 |
Data from Artificial Analysis API — 12 benchmarks
Qwen3 VL 30B A3B Instruct is cheaper overall. Its blended price (3:1 input/output ratio) is $0.35/M tokens vs $0.72/M for Llama 3.2 Instruct 90B (Vision).
Qwen3 VL 30B A3B Instruct wins 11 out of 12 benchmarks compared to 1 for Llama 3.2 Instruct 90B (Vision). See the detailed benchmark chart above for per-category results.
Qwen3 VL 30B A3B Instruct generates tokens faster at 129 tok/s vs 42 tok/s. However, Llama 3.2 Instruct 90B (Vision) has lower time-to-first-token (0.37s vs 0.96s).
Choose based on your priorities: Qwen3 VL 30B A3B Instruct for lower cost, Qwen3 VL 30B A3B Instruct for stronger benchmark performance, and Qwen3 VL 30B A3B Instruct for faster generation. For latency-sensitive apps, check the TTFT comparison above.