Arrakis / Models / Qwen3-8B

Qwen3-8B GPU requirements

Qwen3-8B has 8.2B parameters. To serve it, plan for about 20 GB of GPU memory in 16-bit, 9.8 GB in 8-bit or 4.9 GB in 4-bit, including about 20% for the KV cache and activations.

Deploy this model Check another model

What it takes to serve it

GPU memory to run it for inference, with the smallest GPU setup that holds it and the lowest price on Arrakis right now.

Precision	Memory and the smallest setup
16-bit	20 GB: one RTX 4090 or RTX 3090, RTX 3090 from $0.19 per GPU-hour
8-bit	9.8 GB: one RTX 4090 or RTX 3090, RTX 3090 from $0.19 per GPU-hour
4-bit	4.9 GB: one RTX 4090 or RTX 3090, RTX 3090 from $0.19 per GPU-hour

What it takes to fine-tune it

QLoRA trains adapters on a 4-bit frozen model, LoRA on a 16-bit one, and full fine-tuning updates every weight. Figures are before activations, which grow with batch size and sequence length.

Method	Memory and the smallest setup
QLoRA	5.7 GB: one RTX 4090 or RTX 3090, RTX 3090 from $0.19 per GPU-hour
LoRA	20 GB: one RTX 4090 or RTX 3090, RTX 3090 from $0.19 per GPU-hour
Full fine-tuning	131 GB: one H200, from $4.03 per GPU-hour

About the model

From its card and files on Hugging Face. Memory figures here follow the GPU memory guide.

Parameters: 8.2B
Context window (tokens): 40,960
Published in: BF16
License: apache-2.0
Released: 2025-04-27
Weights: Qwen/Qwen3-8B

Deploy it on Arrakis

Open Models in the console, choose vLLM, SGLang or llama.cpp, and rent a GPU it fits on. You get an OpenAI-compatible endpoint with its own API key, and root SSH to the machine. Or run it yourself on any machine with enough GPU memory:

vLLM

vllm serve Qwen/Qwen3-8B --tensor-parallel-size 1

Deploy this model How deploying works

Questions

Live prices for every GPU are on the GPU prices page.

How much GPU memory does Qwen3-8B need?

To serve it, about 20 GB in 16-bit, 10 GB in 8-bit, 5 GB in 4-bit, including about 20% for the KV cache and activations. To fine-tune it, about 6 GB with QLoRA, 20 GB with LoRA and 131 GB for full fine-tuning with Adam, before activations.

Can I run Qwen3-8B on one GPU?

Yes. In 16-bit it needs about 20 GB, which fits on one RTX 4090 or RTX 3090.

What does it cost to run Qwen3-8B?

In 16-bit it needs one RTX 4090 or RTX 3090; in 4-bit, one RTX 4090 or RTX 3090. Each setup on this page shows the lowest price per GPU-hour on Arrakis right now, and you pay by the hour from a prepaid balance.

How do I deploy Qwen3-8B on Arrakis?

Open Models in the Arrakis console, paste Qwen/Qwen3-8B, choose vLLM, SGLang or llama.cpp, and rent a GPU it fits on. You get an OpenAI-compatible endpoint with its own API key, and root SSH to the machine.

More models

Every model, and a check for any other.