Qwen2.5 72B Instruct (Q2_K) — 23.4 GBon OVH l4-1-gpu
Overview
Qwen2.5 72B Instruct is a 72.71B parameter dense language model by Qwen, with code, multilingual, tool-calls capabilities. It supports a context window of up to 32,768 tokens.
Qwen2.5 72B Instruct is a 72.71-billion-parameter dense transformer from Alibaba's Qwen team, fine-tuned for instruction following, code generation, and multilingual tasks. It competes with other leading 70B instruct models while supporting 14 languages including English, Chinese, Arabic, and Japanese. The model provides native tool calling and structured output capabilities. With a 32K context window and grouped-query attention, it quantizes efficiently for self-hosted inference on high-end consumer or server-class GPU configurations.
At Q2_K quantization (low quality tier), the model weighs 25.45 GB. This exceeds the 24 GB of VRAM on OVH l4-1-gpu. Inference is still possible via CPU offload or memory-mapped loading from disk, but expect significantly reduced performance.
The NVIDIA L4 is a datacenter inference GPU with 24 GB of GDDR6 VRAM and 300 GB/s memory bandwidth. It delivers 121 FP16 TFLOPS with Ada Lovelace architecture. Designed for efficient, low-power inference workloads in cloud and edge deployments. Handles quantized models up to 20B parameters.
Hardware Requirements
| Model size | 25.45 GB |
| VRAM available | 24 GB |
| VRAM used | 23.4 GB |
| System RAM | 80 GB |
| Min RAM required | 3.5 GB |
| GPU layers | 69 / 80 |
| Context size | 670 |
| Backend | cuda13 |
| Flash attention | Yes |
| Reading from disk | Yes |
Performance Notes
Deploy
Prerequisites
Ensure your GPU nodes are prepared with the NVIDIA container toolkit:
ansible-playbook prositronic.infra.nvidia_container_toolkitCommand
helmfile --state-values-file <(curl -s https://www.prositronic.eu/values/qwen2-5-72b-instruct/q2_k/nvidia-l4.yaml) applyGenerated values.yaml
/values/qwen2-5-72b-instruct/q2_k/nvidia-l4.yaml
Loading values…Frequently Asked Questions
How much VRAM does Qwen2.5 72B Instruct (Q2_K) need?
The Q2_K quantization of Qwen2.5 72B Instruct requires 25.45 GB. 69 of 80 layers fit in the 24 GB of VRAM on OVH l4-1-gpu; remaining layers are offloaded to CPU.
Can I run Qwen2.5 72B Instruct on OVH l4-1-gpu?
Yes, with reduced performance. OVH l4-1-gpu can run Qwen2.5 72B Instruct (Q2_K), but only 69 of 80 layers fit in VRAM. The rest are offloaded to CPU.
What is quantization?
Quantization reduces a model's numerical precision from its original floating-point format to a more compact representation. This shrinks the file size and VRAM footprint, making it possible to run large models on consumer hardware. The trade-off is a small reduction in output quality. Q2_K compresses Qwen2.5 72B Instruct from its original size down to 25.45 GB.
What quantization should I choose for Qwen2.5 72B Instruct?
Q2_K is a low-quality quantization. Higher-quality quants (Q8, Q6) preserve more model accuracy but need more VRAM. Lower quants (Q4, Q3, Q2) reduce VRAM usage at the cost of some quality. Choose based on your available hardware and quality requirements.
What is flash attention and why is it enabled?
Flash attention is a memory-efficient algorithm that speeds up the attention mechanism in transformer models. It reduces VRAM usage during inference by avoiding the materialisation of the full attention matrix. For Qwen2.5 72B Instruct on OVH l4-1-gpu, flash attention is enabled to maximise context length and throughput within the available 24 GB of VRAM.
Why are some layers offloaded to CPU?
OVH l4-1-gpu has 24 GB of VRAM, but Qwen2.5 72B Instruct (Q2_K) requires approximately 25.45 GB. Only 69 of 80 layers fit in VRAM; the remaining layers run on CPU, which is slower but still functional.
How do I run Qwen2.5 72B Instruct (Q2_K) with Ollama?
Run ollama run qwen2.5:72b-instruct-q2_k to start Qwen2.5 72B Instruct (Q2_K). Ollama handles downloading the model weights automatically on first run.