Mistral AI/Dense

Mistral-Large 123B

Name: Mistral-Large 123B
Author: Mistral AI

chattool_useThinkingTool Use

123B

Parameters

128K

Context length

Benchmarks

Quantizations

Architecture

Dense

Released

2024-07-24

Layers

KV Heads

Head Dim

128

Family

mistral

Quantization Options

Quant	Bits	VRAM	Quality
IQ2_XXS	2.38	37.1 GB	low
IQ2_M	2.93	45.5 GB	low
Q2_K	3.16	49.1 GB	low
IQ3_XXS	3.25	50.5 GB	low
IQ3_XS	3.5	54.3 GB	low
Q3_K_S	3.64	56.5 GB	low
IQ3_M	3.76	58.3 GB	low
Q3_K_M	4	62.0 GB	low
Q3_K_L	4.3	66.6 GB	moderate
IQ4_XS	4.46	69.1 GB	moderate
Q4_K_S	4.67	72.3 GB	moderate
Q4_K_M	4.89	75.7 GB	good
Q5_K_S	5.57	86.1 GB	good
Q5_K_M	5.7	88.1 GB	good
Q6_K	6.56	101.3 GB	excellent
Q8_0	8.5	131.2 GB	lossless
FP16	16	246.5 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 MISTRAL-LARGE 123B 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 (11)

Arena Elo1267

IFEval84.0

BBH52.7

MMLU-PRO50.7

MATH49.5

GPQA Diamond35.1

GPQA24.9

LiveCodeBench17.8

MUSR17.2

HLE3.4

AIME0.0

Run this model

▸Easiest way to get started·Beginners

DOCS ↗

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

$ollama run mistral:123b-q4_K_M

Downloads and runs automatically. Add --verbose for speed stats.

▸ 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 Ollama Library GGUF Downloads Build Hardware