# Mistral Small 24B Instruct (2409) VRAM Requirements & Hardware Sizing Guide

> **Quick Summary (Answer Capsule)**: Running Mistral Small 24B Instruct (2409) requires 17.82 GB at Q4_K_M (4-bit), 29.91 GB at Q8_0 (8-bit), and 52.61 GB at FP16. Recommended hardware sweet spot: Dual NVIDIA RTX 3060 Rig (24GB VRAM). Scaling context past 32k tokens requires enabling FP8 KV-cache (-ctk q8_0) to prevent CUDA allocation failures.

## Memory Specifications by Precision
| Quantization Format | Precision Level | Required VRAM (8k context) | Quality Retention | Minimum Recommended GPU |
|---|---|---|---|---|
| 4-Bit (Q4_K_M) | Recommended Default | 17.82 GB | >98.2% Perplexity | Dual NVIDIA RTX 3060 Rig (24GB VRAM) |
| 8-Bit (Q8_0) | Near Lossless | 29.91 GB | ~99.9% Perplexity | Workstation / High-Tier GPU |
| 16-Bit (FP16/BF16) | Uncompressed Full | 52.61 GB | 100% Fidelity | Multi-GPU / Datacenter |

## Architectural Memory Analysis
Mistral Small 24B is a dense 24-billion parameter model featuring 56 layers with 32 query heads and 8 GQA key-value heads (`headDim = 128`). Requiring 1.75 GiB of FP16 KV-cache at 8k context and 14.2 GB of Q4_K_M weights, total memory reaches 16.8 GB. It sits directly on the boundary between 16GB and 24GB GPUs, offering exceptional code and reasoning density.

## Tier 1 Free Software Optimization ($0)
On 16GB graphics cards, switch quantization to `IQ4_XS` (13.4 GB weights) and set `OLLAMA_KV_CACHE_TYPE=fp8`. This keeps total memory under 15.2 GB, preventing OOM crashes on the RTX 4060 Ti 16GB and RTX 4070 Ti Super.

## 1-Click Launch Terminal Snippets
- Ollama: `ollama run mistral-small-24b:q4_K_M`
- vLLM: `vllm serve Mistral AI/mistral-small-24b --max-model-len 8192 --gpu-memory-utilization 0.95`

## Verified Hardware & Cloud Pathways
- Amazon Hardware: [RTX 3060 12GB graphics card](https://www.amazon.com/s?k=RTX+3060+12GB+graphics+card&tag=sparecables-20) (rel="noopener sponsored")
- RunPod Cloud Rental: [Deploy Instance](https://runpod.io?ref=ynypzu94) (rel="noopener sponsored")
- Vast.ai Cloud Rental: [Deploy Instance](https://cloud.vast.ai/?ref_id=723130) (rel="noopener sponsored")

---
*Interactive Sizing Calculator available at: https://www.gpugarden.com/vram/mistral-small-24b/*