BenchmarksAlibabaToday
Qwen3 VL 30B A3B Instruct Benchmark Update
Quality: 10/100 | Price: $0.35/M tokens | Output: 114.167 tok/s | MMLU: 0.764% | HumanEval: 0.476%
View sourceQwen
Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception...
Running this yourself: likely needs a rented cloud gpu.
24.7
Quality Score
---
Arena ELO
30B
Parameters
262K
Context
Sign in to join the discussion
0
Downloads
0
Likes
Oct 2025
Released
Benchmarks
19
Open Source
1
Recent launch, pricing, benchmark, and API signals linked to this model or its provider.
Quality: 10/100 | Price: $0.35/M tokens | Output: 114.167 tok/s | MMLU: 0.764% | HumanEval: 0.476%
View sourceQuality: 10/100 | Price: $0.35/M tokens | Output: 114.167 tok/s | MMLU: 0.764% | HumanEval: 0.476%
Quality: 10/100 | Price: $0.35/M tokens | Output: 114.339 tok/s | MMLU: 0.764% | HumanEval: 0.476%
Quality: 10/100 | Price: $0.3/M tokens | Output: 118.65 tok/s | MMLU: 0.764% | HumanEval: 0.476%
View sourceQuality: 10/100 | Price: $0.3/M tokens | Output: 119.638 tok/s | MMLU: 0.764% | HumanEval: 0.476%
View sourceQuality: 10/100 | Price: $0.3/M tokens | Output: 120.324 tok/s | MMLU: 0.764% | HumanEval: 0.476%
View sourceQuality: 10/100 | Price: $0.35/M tokens | Output: 114.339 tok/s | MMLU: 0.764% | HumanEval: 0.476%
Quality: 10/100 | Price: $0.3/M tokens | Output: 118.65 tok/s | MMLU: 0.764% | HumanEval: 0.476%
Quality: 10/100 | Price: $0.3/M tokens | Output: 119.638 tok/s | MMLU: 0.764% | HumanEval: 0.476%
Quality: 10/100 | Price: $0.3/M tokens | Output: 120.324 tok/s | MMLU: 0.764% | HumanEval: 0.476%
Quality: 10/100 | Price: $0.3/M tokens | Output: 123.441 tok/s | MMLU: 0.764% | HumanEval: 0.476%
Quality: 10/100 | Price: $0.3/M tokens | Output: 119.532 tok/s | MMLU: 0.764% | HumanEval: 0.476%
Quality: 10/100 | Price: $0.3/M tokens | Output: 121.043 tok/s | MMLU: 0.764% | HumanEval: 0.476%
Quality: 10/100 | Price: $0.3/M tokens | Output: 121.793 tok/s | MMLU: 0.764% | HumanEval: 0.476%
Quality: 10/100 | Price: $0.3/M tokens | Output: 123.947 tok/s | MMLU: 0.764% | HumanEval: 0.476%
Quality: 10/100 | Price: $0.3/M tokens | Output: 123.873 tok/s | MMLU: 0.764% | HumanEval: 0.476%
Quality: 10/100 | Price: $0.3/M tokens | Output: 122.721 tok/s | MMLU: 0.764% | HumanEval: 0.476%
Quality: 10/100 | Price: $0.3/M tokens | Output: 122.989 tok/s | MMLU: 0.764% | HumanEval: 0.476%
Quality: 10/100 | Price: $0.3/M tokens | Output: 124.419 tok/s | MMLU: 0.764% | HumanEval: 0.476%
Quality: 10/100 | Price: $0.3/M tokens | Output: 126.71 tok/s | MMLU: 0.764% | HumanEval: 0.476%
Quality: 10/100 | Price: $0.3/M tokens | Output: 125.704 tok/s | MMLU: 0.764% | HumanEval: 0.476%
Quality: 10/100 | Price: $0.3/M tokens | Output: 123.993 tok/s | MMLU: 0.764% | HumanEval: 0.476%
Quality: 10/100 | Price: $0.3/M tokens | Output: 124.676 tok/s | MMLU: 0.764% | HumanEval: 0.476%
Quality: 10/100 | Price: $0.3/M tokens | Output: 124.564 tok/s | MMLU: 0.764% | HumanEval: 0.476%
Qwen3 VL 30B A3B Instruct is now available through local Ollama runtime and Ollama Cloud. 256K context window listed. The most powerful vision-language model in the Qwen model family to date.