Mistral Small 24B Instruct 2501 (Q4_K_L) — 21.3 GBon NVIDIA L40S
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 Q4_K_L quantization (low quality tier), the model weighs 13.81 GB. This fits within the 48 GB of VRAM on NVIDIA L40S, enabling full GPU inference.
The NVIDIA L40S is a datacenter GPU with 48 GB of GDDR6 VRAM and 864 GB/s memory bandwidth. It delivers 362 FP16 TFLOPS with Ada Lovelace architecture. A versatile GPU for AI inference, training, and graphics workloads. Handles quantized models up to 40B parameters comfortably.
Hardware Requirements
| Model size | 13.81 GB |
| VRAM available | 48 GB |
| VRAM used | 21.3 GB |
| System RAM | |
| 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/q4_k_l/nvidia-l40s.yaml) applyGenerated values.yaml
/values/mistral-small-24b-instruct-2501/q4_k_l/nvidia-l40s.yaml
Loading values…Frequently Asked Questions
How much VRAM does Mistral Small 24B Instruct 2501 (Q4_K_L) need?
The Q4_K_L quantization of Mistral Small 24B Instruct 2501 requires 13.81 GB. All 40 layers fit in the 48 GB of VRAM available on NVIDIA L40S, enabling full GPU acceleration.
Can I run Mistral Small 24B Instruct 2501 on NVIDIA L40S?
Yes. NVIDIA L40S provides 48 GB of VRAM, which is enough to run Mistral Small 24B Instruct 2501 (Q4_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. Q4_K_L compresses Mistral Small 24B Instruct 2501 from its original size down to 13.81 GB.
What quantization should I choose for Mistral Small 24B Instruct 2501?
Q4_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 NVIDIA L40S, flash attention is enabled to maximise context length and throughput within the available 48 GB of VRAM.
How do I run Mistral Small 24B Instruct 2501 (Q4_K_L) with Ollama?
Run ollama run mistral-small:24b-instruct-2501-q4_k_l to start Mistral Small 24B Instruct 2501 (Q4_K_L). Ollama handles downloading the model weights automatically on first run.