Qwen2.5 72B Instruct (Q6_K) — 67 GBon OVH a100-1-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 Q6_K quantization (high quality tier), the model weighs 55.76 GB. This fits within the 80 GB of VRAM on OVH a100-1-gpu, enabling full GPU inference.
The NVIDIA A100 80 GB is a datacenter GPU with 80 GB of HBM2e VRAM and 2039 GB/s memory bandwidth. It delivers 312 FP16 TFLOPS, enabling fast inference on large language models up to 70B parameters at moderate quantization. Well suited for datacenter teams running production LLM workloads that require high memory capacity and throughput.
Hardware Requirements
| Model size | 55.76 GB |
| VRAM available | 80 GB |
| VRAM used | 67 GB |
| System RAM | 160 GB |
| Min RAM required | 0 GB |
| GPU layers | 80 / 80 |
| Context size | 32,768 |
| Backend | cuda13 |
| Flash attention | Yes |
| Reading from disk | Yes |
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/q6_k/nvidia-a100-80gb.yaml) applyGenerated values.yaml
/values/qwen2-5-72b-instruct/q6_k/nvidia-a100-80gb.yaml
Loading values…Frequently Asked Questions
How much VRAM does Qwen2.5 72B Instruct (Q6_K) need?
The Q6_K quantization of Qwen2.5 72B Instruct requires 55.76 GB. All 80 layers fit in the 80 GB of VRAM available on OVH a100-1-gpu, enabling full GPU acceleration.
Can I run Qwen2.5 72B Instruct on OVH a100-1-gpu?
Yes. OVH a100-1-gpu provides 80 GB of VRAM, which is enough to run Qwen2.5 72B Instruct (Q6_K) with all layers on the GPU for optimal performance.
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. Q6_K compresses Qwen2.5 72B Instruct from its original size down to 55.76 GB.
What quantization should I choose for Qwen2.5 72B Instruct?
Q6_K is a high-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 a100-1-gpu, flash attention is enabled to maximise context length and throughput within the available 80 GB of VRAM.
How do I run Qwen2.5 72B Instruct (Q6_K) with Ollama?
Run ollama run qwen2.5:72b-instruct-q6_k to start Qwen2.5 72B Instruct (Q6_K). Ollama handles downloading the model weights automatically on first run.