Mistral / Mistral Large 3 675B Instruct 2512
Mistral Large 3 675B Instruct 2512 FP8 quantization
Estimated until measured during engineering
Before → After
Base releaseVerified checkpoint
675.000B
675.000B
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 packagingvllm