Qwen3 VL 30B A3B Instruct
Qwen · released Sep 30, 2025 · Qwen/Qwen3-VL-30B-A3B-Instruct
- Type
- Open weightsApache License 2.0
- Params
- 31.1B
- Context
- 262K
3B active per word · about 197K words of context
Our take
Written Sep 2, 2026Qwen3 VL is a vision-language model whose weights can be downloaded under a permissive Apache licence. It handles text and images with a wide request limit, using only 3 billion active parameters from 31.1 billion total.
Pick this for Apache-licensed vision-language work where open weights matter, or when you want a low-cost hosted option with moderate throughput. Use it if you need a wide context window in a compact-active model. Skip it if you need measured quality scores, consistent throughput guarantees, or predictable pricing across providers.
The case for it
- Only 3 billion active parameters from 31.1 billion total — roughly ten-to-one sparsity.
- Apache 2.0 licence allows commercial use, fine-tuning and redistribution.
- 262,144-token request limit, unusually wide for a compact-active model.
- Cheapest hosted option undercuts the next tier by roughly a third.
The case against it
- No measured quality scores in our data — no chat, vision, coding or reasoning benchmarks at all.
- Throughput is inconsistent and unverified on half of hosts, with a fourfold spread where measured.
- Output pricing varies two-and-a-half times across providers with no quality differentiation to justify the spread.
How good is it?
We hold no score for this model.
So there is no figure here for everyday use, coding, agent work or writing. That is a gap in our data, not a low score.
Can you run it yourself?
GeForce RTX 4090 · 24 GB
Borderline fit on an estimated size. It leaves 1.2 GB spare on a size we calculated rather than measured, and a 10% error either way would change the answer.
Comfortable fit
GeForce RTX 5090 · 32 GB
Room to spare. 9.2 GB spare means a 10% error in the size would not change the answer.
Apple M1 Pro (16-core GPU) · 32 GB
Room to spare. 2.4 GB spare means a 10% error in the size would not change the answer.
Memory use by level
Against a 24 GB card.
What is quantisation? →This model on every device we track71 devicesThe Q4 build most people download, on each device: what the weights come to, how much context the memory leaves, and whether it runs. Smallest device that runs it first.
Check against your own machine → · Where to rent it hosted →
Or rent it from someone else
Prices checked between 2 hours and 3 days ago — each listing carries its own date.
The only listing at 262K of context — the other 4 in the table below are not like-for-like. One cheaper row there is outside that comparison: a different context length.
- per 1M tokens
- $0.15 in / $0.60 out
- Context served
- 262K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| Alibaba CloudThrough OpenRouter | $0.13 / $0.52checked 2 hours ago | 131K33K max reply | 45 tok/s | No | Yesunknown period | Unknown |
| DeepInfrafp8Direct and through OpenRouter | $0.15 / $0.60checked 2 hours ago | 262K16K max reply through OpenRouter | 25 tok/sthrough OpenRouter | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterConfirmed |
| OpenRouterOpenRouter's own listing | $0.15 / $0.60checked 2 hours ago | 262K | not measured | Unknown | Unknown | Unknown |
| Novita AIbf16Direct and through OpenRouter | $0.20 / $0.70checked 2 hours ago | 131K33K max reply through OpenRouter | 39 tok/sthrough OpenRouter | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterConfirmed |
| SiliconFlowfp8Through OpenRouter | $0.29 / $1.00checked 3 days ago | 262K236K max reply | 14 tok/s | No | No | Confirmed |
DeepInfra
Novita AIAcross the 5 listings we hold: 4 say they do not train on prompts (2 of them only through OpenRouter), 0 say they do and 1 does not say. 3 appear in the zero-retention registry we check (2 of them only through OpenRouter); the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| Alibaba CloudThrough OpenRouter | ✓ | ✓ | ✓ |
| DeepInfrafp8Direct and through OpenRouter | ✓ | ✓ | ✓ |
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✓ |
| Novita AIbf16Direct and through OpenRouter | ✓ | ✓ | ✓ |
| SiliconFlowfp8Through OpenRouter | ✓ | ✓ | ✓ |
Tool calling: 5 of 5 listings say yes. JSON output: 5 of 5 listings say yes. Strict schema: 5 of 5 listings say yes.
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- No independent board has scored it, so we hold no quality figures at all.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 5 listings does not say whether it trains on prompts, and 2 answer only through OpenRouter, not for their own listing.
- We hold no cached-input rate for any of its listings.
- We hold no batch or off-peak rate for any of its listings.
- We hold a decode speed for it, but no prompt-processing (prefill) figure, so how long the input side of a job takes is unknown to us.
Licence and identifiers
What the licence allowsApache License 2.0, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
Apache License 2.0
Fully permissive: commercial use, redistribution, and derivatives allowed. Requires attribution and a copy of the license. Includes an express patent grant.
Identifiers
- Hugging Face
- Qwen/Qwen3-VL-30B-A3B-Instruct
- Architecture
- Mixture of experts
- Takes in, gives back
- Text and images in, text out
- Catalogue slug
- qwen-qwen3-vl-30b-a3b-instruct