Identity
- Status
- active
- Developer ID
Qwen/Qwen3.5-35B-A3B- Released
- Not reported
- Version
- Qwen3.5-35B-A3B
- License
- apache-2.0
QwenQwen3.5 35B A3B
Qwen3.5-35B-A3B is an open-weight vision-language model published by Qwen.
- Token context
- 262K tokens
- Inputs
- Text, Image
- Outputs
- Text
- Released
- Not reported
Benchmark Market Position
Intelligence, Cost, and Efficiency
Rank #37 of 57
Claude Opus 5.5
GPT-5.5 Pro
Gemini 3.8 Flash- GPT-6.1 Sol
- GPT-6 Astra
- Qwen3.8 Max
DeepSeek V4.1 Flash- Gemini 3.1 Pro
- GPT-5.6 Terra
Grok 4.7
ERNIE 5.1
Kimi K3
GLM 5.3- Qwen3.8 Flash
- Qwen3.7 Plus
- DeepSeek V4 Pro
- GLM 5.3 Flash
Mistral Large 4- Gemma 4 31B
- Qwen3.8 27B
- Qwen3.5 397B A17B
Hy3- Gemma 4 26B A4B
Inkling- Mistral Large 3
- GPT-6 Luna
NVIDIA Nemotron 3 Ultra 550B A55B BF16- Inkling Small
MiniMax M3- Kimi K2.7 Code
- GPT-5.4 Mini
- Gemini 3.5 Flash Lite
- Qwen3.5 35B A3B
- GPT-5.4 Nano
Muse Glimmer 30B
Solar Pro 4- DeepSeek R1
Olmo 3 32B ThinkNova 2 Lite
Command A
Granite 4.2 30B- Granite 4.2 3B
- Granite 4.2 8B
- Llama 4 Maverick 17B 128E Instruct
- Llama 4 Scout 17B 16E Instruct
phi-4- NVIDIA Nemotron 3 Nano 30B A3B BF16
- NVIDIA Nemotron 3.5 Lightning 30B A3B
- GPT-4o
- GPT-4o Mini
- gpt-oss-120b
- gpt-oss-20b
Not ranked in current cohort
Not ranked in current cohort
The orange outline marks Qwen3.5 35B A3B. Each available panel preserves its real rank and value; missing benchmark or pricing inputs remain explicitly unranked.
Providers & Pricing
Estimate workload cost →| Provider | Input / 1M | Output / 1M | Cache read / 1M | Cache write / 1M | Observed | Evidence |
|---|---|---|---|---|---|---|
 DeepinfraAvailable | $0.14 | $1.00 | $0.050 | — | Oct 19, 2026 | Provider-reported |
 OpenrouterAvailable | $0.15 | $1.00 | $0.050 | — | Oct 19, 2026 | Provider-reported |
Benchmarks
All benchmark results →| LMArena Text Arenatext-2026-10-15-a64ca3b12b6e | 1,394.73 | — | 30,457 | qwen3.5-35b-a3b; 95% CI [1390.52780278, 1398.93686884]; votes 30457; rank 161unknown | Original sourcewinner eligible | Third-party benchmark |
At a Glance
Model Facts
Capacity
- Token context
- 262K tokens
- Maximum output
- Unknown
- Total parameters
- 36B
- Active parameters
- 3B
- Knowledge cutoff
- Not reported
Interface and Access
- Inputs
- Text, Image
- Outputs
- Text
- API available
- Yes
- Open weights
- Yes
- Self-hostable
- Yes
- Reasoning
- Yes
- Vision
- Yes
- Tool calling
- Yes
- Capabilities
- chat, generation, reasoning, tools
This page represents one developer model product. Dated API snapshots, serving endpoints, pricing, regions, quantizations, and service tiers attach as versioned aliases or provider details and never create duplicate public model records.
Version Lineage
PredecessorUnknown
SuccessorsUnknown
AliasesQwen/Qwen3.5-35B-A3B, Qwen/Qwen3.5-35B-A3B
Explicit Unknowns
- Release date
- Maximum output
- Knowledge cutoff
Primary Evidence
Sources and Observation Date
Qwen/Qwen3.5-35B-A3B developer model repositoryQwen · observed Aug 28, 2026Qwen/Qwen3.5-35B-A3B README.md at 59d61f3ce65aQwen · observed Aug 28, 2026Deepinfra catalogDeepinfra · observed Oct 19, 2026OpenRouter qwen/qwen3.5-35b-a3b model APIOpenRouter · observed Aug 28, 2026Qwen/Qwen3.5-35B-A3B Hugging Face inference-provider mappingHugging Face · observed Aug 28, 2026Qwen/Qwen3.5-35B-A3B config.json at 59d61f3ce65aQwen · observed Aug 28, 2026Qwen/Qwen3.5-35B-A3B immutable Hub API metadataQwen · observed Aug 28, 2026Qwen/Qwen3.5-35B-A3B tokenizer_config.json at 59d61f3ce65aQwen · observed Aug 28, 2026Hugging Face catalogHugging Face · observed Sep 2, 2026Openrouter catalogOpenrouter · observed Oct 19, 2026Together Ai catalogTogether Ai · observed Oct 19, 2026
Comparable Peers
Related Model Comparisons
| A | Pair | B | Context |
|---|---|---|---|
Qwen3.5 35B A3BQwen | vs | Qwen3.8 27BQwen | family variantsimage, text |
Qwen3.5 35B A3BQwen | vs | Gemma 4 31BGoogle DeepMind | cross-developer peersimage, text |
Qwen3.5 35B A3BQwen | vs | Ministral 3 14B Reasoning 2512Mistral AI | cross-developer peersimage, text |
Qwen3.5 35B A3BQwen | vs | Ministral 3 3B Instruct 2512Mistral AI | cross-developer peersimage, text |
Qwen3.5 35B A3BQwen | vs | Ministral 3 3B Reasoning 2512Mistral AI | cross-developer peersimage, text |
Qwen3.5 35B A3BQwen | vs | Ministral 3 8B Reasoning 2512Mistral AI | cross-developer peersimage, text |
Qwen3.5 35B A3BQwen | vs | Mistral Medium 3.5 128BMistral AI | cross-developer peersimage, text |
Qwen3.5 35B A3BQwen | vs | cross-developer peerstext | |
Qwen3.5 35B A3BQwen | vs | cross-developer peerstext | |
Qwen3.5 35B A3BQwen | vs | family variantstext | |
Qwen3.5 35B A3BQwen | vs | family variantsimage, text | |
Qwen3.5 35B A3BQwen | vs | family variantsimage, text |
Questions
Qwen3.5 35B A3B FAQs
What is Qwen3.5 35B A3B?+
Qwen3.5-35B-A3B is an open-weight vision-language model published by Qwen. It is developed by Qwen and its current sourced lifecycle status is active.
What inputs and outputs does Qwen3.5 35B A3B support?+
Qwen3.5 35B A3B's current record lists Text and Image as input and Text as output.
How much context does Qwen3.5 35B A3B support?+
The current record lists a 262K-token context window and does not report a maximum output length.
Is Qwen3.5 35B A3B available through an API?+
Qwen3.5 35B A3B is marked as API-available. The directly sourced provider records currently include Deepinfra, Hugging Face, Openrouter, and Together Ai.
How large is Qwen3.5 35B A3B?+
The current record lists 36B total parameters and 3B active parameters. Its architecture is Qwen3_5MoeForConditionalGeneration.
What capabilities and tasks does Qwen3.5 35B A3B support?+
Qwen3.5 35B A3B's recorded capabilities are chat, generation, reasoning, and tools. Its supported tasks are image and text.
How much does Qwen3.5 35B A3B cost through an API?+
The lowest directly sourced prices currently attached to Qwen3.5 35B A3B are $0.14 per million input tokens through Deepinfra and $1.00 per million output tokens through Deepinfra. Prices are provider-specific and should be checked against each cited observation date.
Can Qwen3.5 35B A3B be self-hosted?+
Qwen3.5 35B A3B is an open-weight model. Self-hosting is supported, and the recorded license is apache-2.0.
Does Qwen3.5 35B A3B have related versions or aliases?+
No predecessor is recorded. No successor is recorded. Recorded aliases are Qwen/Qwen3.5-35B-A3B.
Which models can Qwen3.5 35B A3B be compared with?+
The current compatible peer set includes Qwen3.8 27B, Gemma 4 31B, Ministral 3 14B Reasoning 2512, Ministral 3 3B Instruct 2512, and Ministral 3 3B Reasoning 2512. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons →