Devstral Small (24B) has 24 billion parameters. At standard 4-bit quantization with 8K context, it needs roughly 18.1 GB of VRAM — weights plus cache and runtime overhead.

VRAM by quantization

PrecisionWeightsCache/BufferTotal VRAM
2-bit (IQ2_XXS)7.7 GB2.9 GB12.6 GB
4-bit (Q4_K_M)13.2 GB2.9 GB18.1 GB
8-bit (Q8_0)25.2 GB2.9 GB30.1 GB
16-bit (FP16)48.0 GB2.9 GB52.9 GB

Which GPU can run Devstral Small (24B) (at 4-bit)?

GPU classVRAMDevstral Small (24B) (18.1 GB)
8 GB · RTX 5060 / 40608 GBWon’t fit
12 GB · RTX 5070 / 306012 GBWon’t fit
16 GB · RTX 5070 Ti / 408016 GBWon’t fit
24 GB · RTX 4090 / 309024 GBFits
32 GB · RTX 509032 GBFits
48 GB · 2×24 / RTX 6000 Ada48 GBFits
128 GB · M-series / RTX Spark128 GBFits

Mistral's agentic coding model tuned for software tasks.

Get the exact number for your setup
Pick your model, quantization, and context length — the calculator shows the full VRAM math and tells you precisely which hardware fits.
Open the Local AI Calculator
Related guides
Best GPU for Llama 3 70B How Much VRAM for DeepSeek-R1 Q4 vs Q8 Quantization Explained Apple Silicon for Local AI RTX Spark: 128GB Unified Memory

VRAM figures are reproducible estimates (weights + KV cache + overhead) and vary by runtime and quant format. Data current as of 2026-06-15.