All models
Alibaba (Qwen)
Qwen3 VL 30B A3B Thinking fastruns locally
alibaba/qwen3-vl-30b-a3b-thinking
Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex tasks. It excels...
Input / 1M
$0.29
USD per million tokens
Output / 1M
$1.00
USD per million tokens
Est. cost / token
$0.000000468
$0.47 per 1M, 3:1 mix
Context window
262K
max output 236K
Major features
VisionOpen weightsReasoningJSON schemaTools
Task suitability (heuristic 1–5, not a benchmark)
- coding3
- reasoning3
- math3
- summarization4
- extraction4
- classification4
- chat3
- creative3
- translation4
- vision3
- long context3
- agentic3
Run it locally
Will it run on my machine? →ollama run qwen3:30b| Quantization | Quality | Memory needed (8K ctx) |
|---|---|---|
| Q2_K | poor | 16.2 GB |
| Q3_K_M | fair | 18.5 GB |
| Q4_K_Mrecommended | good | 22.5 GB |
| Q5_K_M | very good | 25.7 GB |
| Q6_K | excellent | 29.3 GB |
| Q8_0 | near-lossless | 37.2 GB |
| F16 | lossless | 67.8 GB |
Estimates. Mixture-of-experts: memory covers all parameters; only the active ones are used per token, so it runs faster than its size suggests.
Price history
| Recorded | Input | Output | Cached | Source |
|---|---|---|---|---|
| 2026-11-05 03:20 | $0.29 | $1.00 | — | openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $0.29
- Output
- $1.00
- Blended (3:1)
- $0.47
Details
- Company
- Alibaba (Qwen)
- Version
- 3
- Family
- Qwen
- Released
- 2025-10-06
- Parameters
- 31.1B (3B active)
- Max output
- 236K
- Open weights
- Yes
- Inputs
- image, text
- Last synced
- 25 min ago