# Qwen3.8-Flash-Next GPU requirements

Qwen3.8-Flash-Next has 180B parameters. To serve it, plan for about 432 GB of GPU memory in 16-bit, 216 GB in 8-bit or 108 GB in 4-bit, including about 20% for the KV cache and activations.

It is a mixture of experts: 512 experts, 10 of them active for each token. All of them stay in GPU memory, so plan memory for all 180B parameters.

[Deploy it on Arrakis](/console/#/models?model=Qwen/Qwen3.8-Flash-Next).

## What it takes to serve it

| Precision | Memory and the smallest setup |
|---|---|
| 16-bit | 432 GB: 2 × [B300](/gpus/b300.html.md), from $9.20 per hour for all 2 |
| 8-bit | 216 GB: one [B300](/gpus/b300.html.md), from $4.60 per GPU-hour |
| 4-bit | 108 GB: one [H200](/gpus/h200.html.md), from $4.03 per GPU-hour |

## What it takes to fine-tune it

| Method | Memory and the smallest setup |
|---|---|
| QLoRA | 126 GB: one [H200](/gpus/h200.html.md), from $4.03 per GPU-hour |
| LoRA | 432 GB: 2 × [B300](/gpus/b300.html.md), from $9.20 per hour for all 2 |
| Full fine-tuning | 2,880 GB: more than one 8-GPU machine |

## About the model

| | |
|---|---|
| Parameters | `180B` |
| Experts | `512` |
| Experts for each token | `10` |
| Context window (tokens) | `262,144` |
| Published in | `BF16` |
| License | `other` |
| Released | `2026-08-24` |
| Weights | [Qwen/Qwen3.8-Flash-Next](https://huggingface.co/Qwen/Qwen3.8-Flash-Next) |

## Serve it yourself

```
vllm serve Qwen/Qwen3.8-Flash-Next --tensor-parallel-size 2
```

## Questions

**How much GPU memory does Qwen3.8-Flash-Next need?** To serve it, about 432 GB in 16-bit, 216 GB in 8-bit, 108 GB in 4-bit, including about 20% for the KV cache and activations. To fine-tune it, about 126 GB with QLoRA, 432 GB with LoRA and 2,880 GB for full fine-tuning with Adam, before activations.

**Can I run Qwen3.8-Flash-Next on one GPU?** Yes, quantized. In 8-bit it needs about 216 GB, which fits on one B300. In 16-bit it needs 2 B300 GPUs.

**What does it cost to run Qwen3.8-Flash-Next?** In 16-bit it needs 2 B300 GPUs; in 4-bit, one H200. 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 Qwen3.8-Flash-Next on Arrakis?** Open Models in the Arrakis console, paste Qwen/Qwen3.8-Flash-Next, 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: [/models](/models.html.md).