Mistral / Devstral Small 2 24B
FP8 quantization for Devstral Small 2 24B
The published profile is indicative; engineering measurements are completed for the selected model and hardware.
Before → After
Base releaseVerified checkpoint
24.000B
24.000B
QuantizationFP8
Quality retention target
Quality retention target
Production artifactArtifact
Lineage and benchmark report
Lineage and benchmark report
GPU targeting
Weights and KV cacheEstimated until measured during engineering
Estimated VRAMMeasured and certified results are delivered with the project.
Runtime packagingtransformers, vllm, sglang