Llama 3.3 70B Instruct (Q2_K) — 65.8 GBon NVIDIA H100
Overview
Llama 3.3 70B Instruct is a 70B parameter dense language model by Meta, with code, multilingual, tool-calls capabilities. It supports a context window of up to 131,072 tokens.
Llama 3.3 70B Instruct is a 70-billion-parameter dense transformer model from Meta, optimized for instruction following, code generation, and multilingual conversation. It delivers performance competitive with larger models in the Llama family while remaining practical for single-node GPU deployments. The model supports tool calling and eight languages including English, French, Spanish, and German. With a 128K context window and grouped-query attention, it quantizes efficiently down to Q4 levels for self-hosted inference on consumer hardware.
At Q2_K quantization (low quality tier), the model weighs 24.56 GB. This fits within the 80 GB of VRAM on NVIDIA H100, enabling full GPU inference.
The NVIDIA H100 80 GB is a datacenter GPU with 80 GB of HBM3 VRAM and 3350 GB/s memory bandwidth. It delivers 1979 FP16 TFLOPS on the Hopper architecture, making it the fastest single-GPU option for large language model inference. It handles models up to 70B parameters with high throughput. Built for datacenter teams running demanding production AI workloads.
Hardware Requirements
| Model size | 24.56 GB |
| VRAM available | 80 GB |
| VRAM used | 65.8 GB |
| System RAM | |
| Min RAM required | 0 GB |
| GPU layers | 80 / 80 |
| Context size | 131,072 |
| 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/llama-3-3-70b-instruct/q2_k/nvidia-h100-80gb.yaml) applyGenerated values.yaml
/values/llama-3-3-70b-instruct/q2_k/nvidia-h100-80gb.yaml
Loading values…Frequently Asked Questions
How much VRAM does Llama 3.3 70B Instruct (Q2_K) need?
The Q2_K quantization of Llama 3.3 70B Instruct requires 24.56 GB. All 80 layers fit in the 80 GB of VRAM available on NVIDIA H100, enabling full GPU acceleration.
Can I run Llama 3.3 70B Instruct on NVIDIA H100?
Yes. NVIDIA H100 provides 80 GB of VRAM, which is enough to run Llama 3.3 70B Instruct (Q2_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. Q2_K compresses Llama 3.3 70B Instruct from its original size down to 24.56 GB.
What quantization should I choose for Llama 3.3 70B 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 Llama 3.3 70B Instruct on NVIDIA H100, flash attention is enabled to maximise context length and throughput within the available 80 GB of VRAM.
How do I run Llama 3.3 70B Instruct (Q2_K) with Ollama?
Run ollama run llama3.3:70b-instruct-q2_k to start Llama 3.3 70B Instruct (Q2_K). Ollama handles downloading the model weights automatically on first run.