Ministral-3-3B-Instruct-2512

Checkpointmistralai/Ministral-3-3B-Instruct-2512Model card indexedModel card

Support summary

Ministral-3-3B-Instruct-2512 is a checkpoint published by Mistral AI, built on the MistralForCausalLM, PixtralForConditionalGeneration, and Mistral3ForConditionalGeneration architectures. vLLM 0.28.0, the newest indexed vLLM release, documents support. TensorRT-LLM lists its architecture, but not this exact checkpoint.

vLLM documents support in 20 of 20 indexed releases, from 0.17.0 to 0.28.0.

Documented quantization
FP8
Configured context
262,144 tokens
License
apache-2.0

Hardware, quantization and features count only statements about this checkpoint; engine-wide capabilities are listed with each release.

Hugging Face model card
Publisher
Mistral AI
License
apache-2.0
Library
vllm
Architecture
Mistral3ForConditionalGeneration
Weight tensor elements
3.8B
Tensor types
BF16, F8_E4M3
Quantization
fp8
Configured context
262,144 tokens
Languages
en, fr, es, de, it, pt, nl, zh, ja, ko, ar
Base models
mistralai/Ministral-3-3B-Base-2512
Weight access
Public
Repository created
2025-10-31
Source 1: mistralai/Ministral-3-3B-Instruct-2512 · publisher model cardSource 2: mistralai/Ministral-3-3B-Instruct-2512 · Hugging Face metadataSource 3: mistralai/Ministral-3-3B-Instruct-2512 · publisher configurationReviewed
Model notes and sources

Engine support

3 engines

Engine support for Ministral-3-3B-Instruct-2512
EngineReleaseCheckpoint supportEvidence scopeLast known supported
vLLM0.28.0Newest indexedCheckpoint evidenceSource: vLLM v0.28.0 · docs/models/supported_models.mdReviewed 0.28.0This release
Features, dependencies and evidence for vLLM 0.28.0
SGLang0.5.19Newest indexedNo matching evidence curatedNo supported release indexed
Features, dependencies and evidence for SGLang 0.5.19
TensorRT-LLM1.2.1Newest indexedArchitecture listed; exact checkpoint unknownNo supported release indexed
Features, dependencies and evidence for TensorRT-LLM 1.2.1

Recipes and cookbooks