Mistral Small 24B Instruct 2501 (Q2_K_L) — 16.4 GBon OVH a100-1-gpu
Overview
Mistral Small 24B Instruct 2501 is a 23.57B parameter dense language model by Mistral AI, with code, multilingual, tool-calls capabilities. It supports a context window of up to 32,768 tokens.
Mistral Small 24B Instruct 2501 is a 23.57-billion-parameter dense transformer from Mistral AI, optimized for instruction following, code generation, and multilingual conversation. It occupies a mid-range parameter class that offers strong performance relative to its size, competing with larger 30B models on many benchmarks. The model supports tool calling and 10 languages including English, French, Chinese, and Japanese. With a 32K context window and flash attention, it fits on a single consumer GPU at Q4 quantization for efficient self-hosted inference.
At Q2_K_L quantization (low quality tier), the model weighs 8.89 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 | 8.89 GB |
| VRAM available | 80 GB |
| VRAM used | 16.4 GB |
| System RAM | 160 GB |
| Min RAM required | 0 GB |
| GPU layers | 40 / 40 |
| 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/mistral-small-24b-instruct-2501/q2_k_l/nvidia-a100-80gb.yaml) applyGenerated values.yaml
/values/mistral-small-24b-instruct-2501/q2_k_l/nvidia-a100-80gb.yaml
Loading values…Frequently Asked Questions
How much VRAM does Mistral Small 24B Instruct 2501 (Q2_K_L) need?
The Q2_K_L quantization of Mistral Small 24B Instruct 2501 requires 8.89 GB. All 40 layers fit in the 80 GB of VRAM available on OVH a100-1-gpu, enabling full GPU acceleration.
Can I run Mistral Small 24B Instruct 2501 on OVH a100-1-gpu?
Yes. OVH a100-1-gpu provides 80 GB of VRAM, which is enough to run Mistral Small 24B Instruct 2501 (Q2_K_L) 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_L compresses Mistral Small 24B Instruct 2501 from its original size down to 8.89 GB.
What quantization should I choose for Mistral Small 24B Instruct 2501?
Q2_K_L 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 Mistral Small 24B Instruct 2501 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 Mistral Small 24B Instruct 2501 (Q2_K_L) with Ollama?
Run ollama run mistral-small:24b-instruct-2501-q2_k_l to start Mistral Small 24B Instruct 2501 (Q2_K_L). Ollama handles downloading the model weights automatically on first run.