← Leaderboard
Qwen3 VL 30B A3B Instruct
Open source
Self-hostable
Free to run
Alibaba (Qwen)
Open license
text
vision
Released 1y agoAvg score
50.0
/ 100 · not enough data for the index
Context
262k
Output limit
16k
Input price
$0.15 /M
Output price
$0.60 /M
Parameters
31.1B · 3B active
Est. VRAM (Q4)
~18.7 GB
Public list price, verified 8h ago
Added automatically from the public model catalog. Family and licence details are not curated yet; benchmark scores appear as upstream leaderboards list this model.
Benchmarks
performance
Output SpeedN/A
tok/sMedian output speed in tokens per second over the last 14 days on the model maker's own API, measured nightly with a fixed ~800-token prompt and ~250-token answer. Models not yet probed fall back to a dated manual figure. Higher is faster.
Time to First TokenN/A
msMedian time from request to first streamed token in milliseconds over the last 14 days on the model maker's own API, using the same nightly probe prompt. Lower is snappier; reasoning models are penalised here because they think before talking.
Reliability monitor
Loading drift signal…
Hosted endpoints
| Host | Input $/M | Output $/M | Context | Speed | TTFT | Uptime 24h | Quant |
|---|---|---|---|---|---|---|---|
| Host 37 | $0.15 | $0.60 | 262k | 25 tok/s | 0.43 s | 99.4% | fp8 |
| Host 27 | $0.20 | $0.70 | 131k | 43 tok/s | 1.59 s | 95.0% | bf16 |
| Host 43 | $0.29 | $1.00 | 262k | — | — | 90.6% | fp8 |
Anonymised third-party hosts. Sorted by lowest output price. Speed and time to first token are medians from our nightly probe where measured; uptime is the catalog's 24-hour figure.