>>

Run Qwen3.5-4B-Qwen3.8-27B-Draft on Lium

NVIDIA · Text generation · 4.2B parameters · 8.4 GB BF16 weights · released 2026-11-11
It needs about 11 GB of VRAM. The cheapest setup that runs it is RTX 5060 Ti (16 GB), from $0.15 per hour, billed per second.

Other GPUs that run it

RTX A450020 GBfrom $0.17 / hourRent
2x CMP 170HX16 GBfrom $0.80 / hourRent

How to run it

Rent the pod above, open a terminal over SSH or Jupyter and serve nvidia/Qwen3.5-4B-Qwen3.8-27B-Draft:
vllm serve nvidia/Qwen3.5-4B-Qwen3.8-27B-Draft
Claude Code and Codex can do all of it through the Lium CLI.

Frequently asked questions

How much VRAM does Qwen3.5-4B-Qwen3.8-27B-Draft need?

About 8.4 GB for the released BF16 weights, so plan on 11 GB with room for activations and KV cache at a short context. Longer contexts and bigger batches need more.

What GPU should I rent to run Qwen3.5-4B-Qwen3.8-27B-Draft?

RTX 5060 Ti (16 GB). On Lium that setup costs from $0.15 per hour, billed per second with no minimum.
All open models
For AI agents (CLI install, agent skill, headless signup): llms-full.txt