Qwen3 Omni 30B A3B
Model overview
Qwen3-Omni-30B-A3B-Instruct
Qwen's current public Qwen3 Omni 30B A3B open-weight omni-modal family.
general LLMreasoningmultimodalvision-languageaudiospeechchatvoice assistantlocal inference
Representative version
Qwen3-Omni-30B-A3B-Instruct
| Company | Alibaba / Qwen |
|---|---|
| Representative basis | Variant referenced by model provenance 2026-07-15 |
| Release | Not disclosed |
| Release type | Model release |
| Parameters | 30B / 3B active |
| Architecture | Not disclosed |
| Context | Not disclosed |
| Input modalities | text / image / audio / video |
| Output modalities | text / audio |
| Tool use / function calling | Not disclosed |
| Structured output / reasoning | Confirmed: Reasoning |
| Vision / audio / video | Confirmed: Vision, Audio, Video |
| Open weights / License | Weights available / Apache-2.0 License sourcealibaba-qwen-qwen3-omni-30b-a3b-instruct-current · 2026-07-15 |
| Vendor API | Not disclosed API source pending verification |
| OpenRouter | Not separately listed on OpenRouter |
| Pricing | No reliable public source |
| Benchmark | No reliable public source |
| Public signals | 1 runtime / access record / 1 community discussion / 2 activity snapshots |
| Use cases | assistant chat / voice assistant / local inference / general text tasks |
| Claim evidence | Release / model specs / weightsQwen/Qwen3-Omni-30B-A3B-Instruct · Hugging FaceQwen3-Omni-30B-A3B-Instruct |
OpenRouter
Pricing / context / availability
| OpenRouter | Not separately listed on OpenRouter |
|---|---|
| OpenRouter listing | Not separately listed in the current OpenRouter public list |
| Mapped version | Qwen3-Omni-30B-A3B-Instruct alibaba-qwen-qwen3-omni-30b-a3b-instruct-current |
| Pricing | No reliable public source |
| Context | Not disclosed |
| Speed/Latency | No reliable public source |
| Snapshot time | 2026-07-15T20:11:41.551Z |
| Source | View source |
Public activity counters
Cumulative Hugging Face model-card downloads / likes / spaces
| Platform | Entry | Downloads | Likes | Spaces | Time | Source |
|---|---|---|---|---|---|---|
| huggingface | Qwen/Qwen3-Omni-30B-A3B-Instruct | 1,807,711 | 957 | 31 | 2026-07-15T20:11:41.551Z | View source |
| huggingface | Qwen/Qwen3-Omni-30B-A3B-Thinking | 362,765 | 311 | 12 | 2026-07-15T20:11:41.551Z | View source |
Operations
Runtime / access signals
| Time | Signal | Original text | Source |
|---|---|---|---|
| 06/13/2026, 03:47 PM UTC | Severe generation length bottleneck (hardcoded at 1024 tokens) in Qwen3OmniMoeForConditionalGeneration duri... | Hello, I‘m experiencing a persistent, unbreakable token truncation precisely at 1024 generated tokens (excluding prompt tokens). Even when I e... | Source |
Vertical comparison
Current available versions
| Version | Release | Parameters | Context | Input | Output | Open weights / License | Vendor API | Source tier |
|---|---|---|---|---|---|---|---|---|
| Qwen3-Omni-30B-A3B-Instruct | Not disclosed | 30B / 3B active | Not disclosed | text / image / audio / video | text / audio | Weights available / Apache-2.0 | Not disclosed | P0 |
| Qwen3-Omni-30B-A3B-Thinking | Not disclosed | 30B / 3B active | Not disclosed | text / image / audio / video | text | Weights available / Apache-2.0 | Not disclosed | P0 |
Evidence gaps
Public display boundary
Release date not disclosedOpenRouter not separately verifiedNo reliable benchmark sourceNo linkable real reviewSpeed/latency not disclosed