Databricks/Mixture of Experts

DDBRX 132B

Name: DBRX 132B
Author: Databricks

Databricks DBRX — 132B MoE with 36B active params. Strong coding and general reasoning.

chatcoding

132B

Parameters (36B active)

32K

Context length

Benchmarks

Quantizations

30K

HF downloads

Architecture

MoE

Released

2024-03-27

Layers

KV Heads

Head Dim

128

Family

dbrx

Quantization Options

Quant	Bits	VRAM	Quality
IQ2_XXS	2.38	39.8 GB	low
IQ2_M	2.93	48.8 GB	low
Q2_K	3.16	52.6 GB	low
IQ3_XXS	3.25	54.1 GB	low
IQ3_XS	3.5	58.2 GB	low
Q3_K_S	3.64	60.5 GB	low
IQ3_M	3.76	62.5 GB	low
Q3_K_M	4	66.5 GB	low
Q3_K_L	4.3	71.4 GB	moderate
IQ4_XS	4.46	74.1 GB	moderate
Q4_K_S	4.67	77.5 GB	moderate
Q4_K_M	4.89	81.2 GB	good
Q5_K_S	5.57	92.4 GB	good
Q5_K_M	5.7	94.5 GB	good
Q6_K	6.56	108.7 GB	excellent
Q8_0	8.5	140.7 GB	lossless
FP16	16	264.5 GB	lossless

Select your GPU above to see speed estimates and compatibility for each quantization.

▸ READY TO RUN THIS?RENT BY THE HOUR

RENT A GPU AND RUN DBRX 132B NOW

Rent on RunPod →Or Vast.ai →

Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.

Community Ratings

Loading ratings...

Benchmarks (7)

HumanEval70.1

MATH66.9

IFEval62.0

BBH56.0

MMLU-PRO45.0

GPQA12.2

MUSR12.2

Run this model

▸Easiest way to get started·Beginners

DOCS ↗

curl -fsSL https://ollama.com/install.sh | sh

$ollama run dbrx:132b-q4_K_M

Tag may need adjustment — check ollama.com/library/dbrx for available tags.

▸ SETUP GUIDE

Auto-setup with fitmyllm CLI

Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.

pip install fitmyllmthen run fitmyllmLearn more

Auto-detect GPULive tok/s in chatSpeed benchmarks9 inference engines

HuggingFace GGUF Downloads Build Hardware