Qwen 3.6 35B A3B — Multimodal LLM AI Model
Qwen 3.6 35B A3B is a mixture-of-experts vision-language model — 35B parameters total but only 3B active per token, so it answers fast for its size. 256K context, and strong on agentic coding and repo-scale reasoning.
What it does
Qwen3.6-35B-A3B is the newest of Alibaba's Qwen models, built in response to developer feedback on Qwen3.5.
It is general-purpose and multimodal — text, images and video — but its distinguishing strength is agentic coding: planning, writing, debugging and running software work across a whole repository rather than a single file.
When to use it
- Software work across a repository rather than a single file
- Frontier-level output at a lower cost, since only 3B parameters activate
- Hard problems that benefit from reasoning before answering
- Long conversations, with earlier reasoning carried forward
- Whole codebases at once, on a native 262K token context
Details
- CategoryMultimodal LLM
- Year2026
- LicenseApache-2.0
Compliance & Provenance
- ProviderAlibaba (open weights) · GPAI
- EU AI Act RiskLimited Risk
- Art. 50 TransparencyRequired — AI-generated outputs are marked
Inputs & Outputs
- TextInputstring
Text prompt or question
- Image 1Inputimageoptional
Optional reference image for visual understanding. When provided, the model analyzes the image content together with the text prompt. Supports up to 4096x4096 resolution.
- Image 2Inputimageoptional
Optional second reference image. When provided alongside Image 1, the model can compare, contrast, or jointly reason over both images with the text prompt. Supports up to 4096x4096 resolution.
- TextOutputstring
Generated text response
Parameters
- max_new_tokensintegerdefault 2048range 1–8192advanced
Max new tokens (1-8192)
Maximum number of tokens the model may generate in the response. Default 2048. Lower for terse answers / cost saving; raise (up to 8192) for long-form generation. Generation also stops at natural end-of-sequence regardless of this cap.
- temperaturefloatdefault 0.7range 0–2advanced
Temperature (0-2)
Sampling temperature. 0.0 = greedy / deterministic (best for factual Q&A, OCR, code). 0.7 (default) = balanced creativity. >1.0 = more divergent / creative. Raise for brainstorming, lower for precision tasks.
- top_pfloatdefault 0.8range 0–1advanced
Top-p (nucleus)
Nucleus sampling threshold — keeps the smallest set of tokens whose cumulative probability ≥ top_p, samples from that set. 1.0 = unrestricted, 0.8-0.95 (typical defaults) = balanced. Lower values produce more focused output. Combined with top_k.
- top_kintegerdefault 20range 1–100advanced
Top-k
Top-k sampling — restricts the candidate set to the k highest-probability tokens. 50 is permissive, 20 (Qwen default) is tighter. Lower for more deterministic output, higher for variety.
- enable_thinkingbooleandefault Offoptions: On, Offadvanced
Thinking mode (On/Off)
When 'On', Qwen 3.6 runs an internal chain-of-thought before answering — better quality on multi-step reasoning, agentic coding, and complex visual analysis, at the cost of higher latency and token count. Default 'Off' for fast simple replies. Switch on for benchmarks, hard reasoning, or repository-level coding tasks.
Tags
Alternatives in Multimodal Language Models
- Agnes-3.0-Flash
Agnes 3.0 Flash Preview — 33B hybrid-attention vision-language model, 262K context, bf16. Open-weights preview checkpoint, distinct from the production Agnes 3.0 Flash.
- Gemma 4 31B
Gemma 4 31B Dense flagship VLM, 256K context, thinking mode.
- Gemma4-E2B
Gemma 4 E2B compact VLM, 128K context, bf16.
- Mage-VL
Mage-VL — 4B codec-native streaming multimodal model from Microsoft. A from-scratch Mage-ViT visual encoder on a Qwen3-4B decoder, trained to read images and video through codec structure rather than uniform frame sampling. This entry serves its image-and-text mode; its video and proactive-streaming modes are not wired up here.
- Qwen3.8-27B
Qwen 3.8 27B Dense VLM, 256K context, bf16.