Qwen
Qwen3.6 35B A3B
Qwen's 35B-parameter mixture-of-experts (3B active) open vision-language model with a 256K-token context, ready to serve on Runpod Serverless with vLLM or on a Pod.
Qwen3.6 35B A3B
Specifications
Provider
Qwen
Modality
Vision + language
Task
Text generation
Parameters
35B
Active parameters
3B
Context
256K tokens
Precision
BF16
Weights
72
License
apache-2.0
Released
2026-04-14
Endpoint ID
Weights on Hugging Face
Qwen/Qwen3.6-35B-A3B
Frequently asked questions
How do I deploy Qwen3.6 35B A3B on Runpod?
Deploy the vLLM worker from the Runpod Hub as a Serverless endpoint and set MODEL_NAME to Qwen/Qwen3.6-35B-A3B. The endpoint is OpenAI-compatible and scales to zero when idle. You can also run vLLM on a Pod.
What GPU do I need to run Qwen3.6 35B A3B?
Start with RTX PRO 6000 (96 GB VRAM). The weights take about 72 GB; longer contexts and more concurrent requests need extra memory for the KV cache.
How much does Qwen3.6 35B A3B cost on Runpod?
Serverless endpoints and Pods bill per second for the GPU you choose. A Serverless endpoint costs nothing while scaled to zero.
qwen-qwen3-6-35b-a3b
Qwen/Qwen3.6-35B-A3B
Vision + language
2026-04-14 17:00
RTX PRO 6000