Arrakis / Models / Qwen2.5-14B-Instruct

Qwen2.5-14B-Instruct GPU requirements

Qwen2.5-14B-Instruct has 15B parameters. To serve it, plan for about 35 GB of GPU memory in 16-bit, 18 GB in 8-bit or 8.9 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	35 GB: one L40S, RTX 6000 Ada or RTX A6000, L40S from $0.44 per GPU-hour
8-bit	18 GB: one RTX 4090 or RTX 3090, RTX 3090 from $0.19 per GPU-hour
4-bit	8.9 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	10 GB: one RTX 4090 or RTX 3090, RTX 3090 from $0.19 per GPU-hour
LoRA	35 GB: one L40S, RTX 6000 Ada or RTX A6000, L40S from $0.44 per GPU-hour
Full fine-tuning	236 GB: one B300, from $4.60 per GPU-hour

About the model

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

Parameters: 15B
Context window (tokens): 32,768
Published in: BF16
License: apache-2.0
Released: 2024-09-16
Weights: Qwen/Qwen2.5-14B-Instruct

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/Qwen2.5-14B-Instruct --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 Qwen2.5-14B-Instruct need?

To serve it, about 35 GB in 16-bit, 18 GB in 8-bit, 9 GB in 4-bit, including about 20% for the KV cache and activations. To fine-tune it, about 10 GB with QLoRA, 35 GB with LoRA and 236 GB for full fine-tuning with Adam, before activations.

Can I run Qwen2.5-14B-Instruct on one GPU?

Yes. In 16-bit it needs about 35 GB, which fits on one L40S, RTX 6000 Ada or RTX A6000.

What does it cost to run Qwen2.5-14B-Instruct?

In 16-bit it needs one L40S, RTX 6000 Ada or RTX A6000; 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 Qwen2.5-14B-Instruct on Arrakis?

Open Models in the Arrakis console, paste Qwen/Qwen2.5-14B-Instruct, 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.