mistral-large-3

Name: mistral-large-3
Author: Ollama

apache-2.0675B

A general-purpose multimodal mixture-of-experts model for production-grade tasks and enterprise workloads.

Context

262K

Capabilities

Show unsupported (6)

Infrastructure

Streaming

Fine-tuning

ProviderOllama

Licenseapache-2.0

Status—

Typechat

Input modalitiestext

Output modalitiestext

Open weightYes

Parameters675B

Architecture—

Context window262K tokens

Max input—

Max output—

Reasoning tokens—

Knowledge cutoff—

Release date2025-12-02

Sourceofficial

Model	Caps	Perf	Speed	Context	Max out
mistral-large-3	SF	—	—	262K	—
mistral-large-4	TSF	—	—	1M	—

GET/v1/models/ollama/mistral-large-3