Model · Alibaba · Text
Qwen3.6 35B-A3B
Alibaba's open-weight flagship from the Qwen3.6 generation. MoE architecture with 35B total / 3B active parameters; natively multimodal (text + vision) with up to ~1M-token context. Superseded by Qwen3.8.
- Modality
- Text
- License
- Qwen License (Open weights)
- Parameter size
- 35B (3B active)
- Released
- April 17, 2026
- Last verified
- September 8, 2026
- Runs locally
- Yes
- Also handles
- vision
Strengths
- Strong multilingual and Chinese-language performance
- MoE architecture — fast inference for the parameter count
- Native vision capability
- Strong coding and math performance
Weaknesses
- License restricts commercial use at >100M MAU
- Needs serious GPU footprint for self-hosting
Try it
| Where | Type | Notes |
|---|---|---|
| Hugging Face | weights | Qwen License (Apache-2.0 weights; quantizations available) |
| Ollama | local | Quantized variants available |
Official sources
- Model card model
Change log
- — Superseded by Qwen3.8 27B (August 2026). Note the filename is a legacy artifact of the corrected 2026-06-08 entry and no longer matches the title.
- — Replaced fabricated 'Qwen 3.5 122B' entry (no such repo) with the real current open-weight flagship Qwen3.6-35B-A3B (released 2026-04-17). The real Qwen3.5 flagship was Qwen3.5-397B-A17B (2026-02-16).
- — Initial entry. Sighted on Hugging Face (lastModified 2026-04-24).
Esc