DBRX Instruct

Overview

Databricks' 132B MoE with 36B active params, trained on 12T tokens — state-of-the-art at March 2024 release but largely surpassed by DeepSeek V3 and R1.

When to pick this model

• Databricks-native pipelines that need an in-house model
• Code and math workloads where 36B active params shine
• Research comparisons against modern frontier MoEs
• Multi-GPU deployments already provisioned for 100B+ models
• Internal evals before migrating to DeepSeek V3 or R1

VRAM requirements by quantization

VRAM figures include model weights plus a typical 8k KV cache and ~600 MB runtime overhead (Ollama / llama.cpp baseline). Add headroom for higher context lengths.

Published benchmark scores

Scores published by the model author or aggregated from public leaderboards. Re-measured monthly by our editorial team.

Strengths

• State-of-the-art quality at March 2024 release
• Strong on code and math benchmarks
• Databricks Open Model License is broadly permissive
• 12T tokens of high-quality training data

Limitations

• ~76 GB VRAM at Q4 demands multi-GPU serving
• Largely outclassed by DeepSeek V3 and R1 in 2025
• HuggingFace repo is gated, slowing access

Architecture & training

Architecture: MoE · 132B total / 36B active · 16 experts, 4 active per token

Training: Databricks — 12T high-quality tokens, strong in code and science.

Quick start

ollama run dbrx

Or use the open-source MCP server to query this model from Claude Desktop, Cursor, or any MCP-compatible client.