LLM
How to deploy Qwen3.6-35B-A3B on a GPU cloud
A 36B (MoE) language model for chat and instruction-following. Full specs, license and use cases.
Qwen3.6-35B-A3B size and hardware requirements
36.0B
Total parameters
~3B active per token (mixture-of-experts; see total parameters above)
Active parameters
BF16
Published precision
80.4 GB
Min VRAM (native)
| Precision | Weight size on disk | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| BF16 | 67.0 GB | 80.4 GB | RTX PRO 6000 | 1 | $1.64/hr |
| FP8 (quantized) | 33.5 GB | 40.2 GB | RTX 6000 Ada | 1 | $0.524/hr |
| INT4 (quantized) | 16.7 GB | 20.1 GB | RTX 3090 | 1 | $0.147/hr |
How to run Qwen3.6-35B-A3B
Run Qwen3.6-35B-A3B with vLLM
Generic example, not from the model's own docs: adjust flags (quantization, context length, parallelism) for your setup.
vllm serve Qwen/Qwen3.6-35B-A3B --tensor-parallel-size 1Run Qwen3.6-35B-A3B with Ollama
Verified against Ollama's own library listing.
ollama run qwen3.6:35bRun Qwen3.6-35B-A3B with GGUF quantizations
Prebuilt GGUF weights published at unsloth/Qwen3.6-35B-A3B-GGUF. Run with llama.cpp's llama-server or load the repo directly in LM Studio.
llama-server -hf unsloth/Qwen3.6-35B-A3B-GGUFDeploy Qwen3.6-35B-A3B on Aquanode
Aquanode has no one-click deploy template for Qwen3.6-35B-A3B; you install the inference engine yourself with the commands below. Aquanode sells GPU pods billed per second, not a hosted inference API.
- Launch a bare GPU pod sized to the requirement above (1× RTX PRO 6000 or larger).
- Open a terminal on the pod, or save one of the commands above as a startup script so it runs automatically the first time the pod boots.
- Run the command and connect to the resulting endpoint.
Launch a GPU pod