FitMyLLM
Mistral AI/Mixture of Experts

Mistral AIMixtral-8x7B

Mixtral 8x7B — groundbreaking open MoE. Runs at 13B speed with 47B total params.

chatcoding
46.7B
Parameters (13B active)
32K
Context length
13
Benchmarks
14
Quantizations
780K
HF downloads
Architecture
MoE
Released
2024-01-11
Layers
32
KV Heads
8
Head Dim
128
Family
mistral

Quantization Options

QuantBitsVRAMQuality
IQ3_XXS3.2519.5 GBlow
IQ3_XS3.520.9 GBlow
Q3_K_S3.6421.7 GBlow
IQ3_M3.7622.4 GBlow
Q3_K_M423.8 GBlow
Q3_K_L4.325.6 GBmoderate
IQ4_XS4.4626.5 GBmoderate
Q4_K_S4.6727.7 GBmoderate
Q4_K_M4.8929.0 GBgood
Q5_K_S5.5733.0 GBgood
Q5_K_M5.733.8 GBgood
Q6_K6.5638.8 GBexcellent
Q8_08.550.1 GBlossless
FP161693.9 GBlossless

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 MIXTRAL-8X7B 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 (13)

IFEval59.0
BBH37.1
MATH-50029.9
MMLU-PRO29.6
GPQA Diamond29.2
MUSR16.7
MATH12.2
GPQA9.5
AA Intelligence7.7
LiveCodeBench6.6
HLE4.5
SciCode2.8
AIME0.0

Run this model

▸Easiest way to get started·Beginners
DOCS ↗
curl -fsSL https://ollama.com/install.sh | sh
$ollama run mixtral:46.7b-instruct-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
HuggingFaceOllama LibraryGGUF DownloadsBuild Hardware

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

NVIDIA RTX 5090
32 GB VRAM • 1792 GB/s
NVIDIA
$1999
AmazonNeweggeBayPCPartPicker
Apple M1 Max (32GB)
32 GB VRAM • 400 GB/s
APPLE
$1499
Apple M2 Max (32GB)
32 GB VRAM • 400 GB/s
APPLE
$1799
NVIDIA V100 SXM2 32GB
32 GB VRAM • 900 GB/s
NVIDIA
$3500
Apple M2 Pro (32GB)
32 GB VRAM • 200 GB/s
APPLE
$1499
Apple M4 (32GB)
32 GB VRAM • 120 GB/s
APPLE
$1199
NVIDIA Tesla V100 DGXS 32 GB
32 GB VRAM • 897 GB/s
NVIDIA
NVIDIA Tesla V100 PCIe 32 GB
32 GB VRAM • 897 GB/s
NVIDIA
NVIDIA Tesla V100 SXM2 32 GB
32 GB VRAM • 898 GB/s
NVIDIA
NVIDIA Tesla V100 SXM3 32 GB
32 GB VRAM • 981 GB/s
NVIDIA
AMD Radeon Instinct MI60
32 GB VRAM • 1020 GB/s
AMD
NVIDIA Tesla V100S PCIe 32 GB
32 GB VRAM • 1130 GB/s
NVIDIA
AMD Radeon Instinct MI100
32 GB VRAM • 1230 GB/s
AMD
$5000
NVIDIA RTX 5000 Ada Generation
32 GB VRAM • 576 GB/s
NVIDIA
$4000
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce RTX 5090
32 GB VRAM • 1790 GB/s
NVIDIA
$1999
AmazonNeweggeBayPCPartPicker
NVIDIA GeForce RTX 5090 D
32 GB VRAM • 1790 GB/s
NVIDIA
$1999
AmazonNeweggeBayPCPartPicker
NVIDIA Jetson AGX Xavier 32 GB
32 GB VRAM • 136 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA Quadro GV100
32 GB VRAM • 868 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA TITAN V CEO Edition
32 GB VRAM • 868 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
NVIDIA Tesla PG500-216
32 GB VRAM • 1130 GB/s
NVIDIA
NVIDIA Tesla PG503-216
32 GB VRAM • 1130 GB/s
NVIDIA
AMD Radeon Pro Vega II
32 GB VRAM • 825 GB/s
AMD
AmazonNeweggeBayPCPartPicker
AMD Radeon Pro Vega II Duo
32 GB VRAM • 1020 GB/s
AMD
AmazonNeweggeBayPCPartPicker
AMD Radeon PRO V620
32 GB VRAM • 512 GB/s
AMD
AmazonNeweggeBayPCPartPicker
AMD Radeon PRO W6800
32 GB VRAM • 512 GB/s
AMD
$2249
AmazonNeweggeBayPCPartPicker
AMD Radeon Pro W6800X
32 GB VRAM • 512 GB/s
AMD
AmazonNeweggeBayPCPartPicker
AMD Radeon Pro W6800X Duo
32 GB VRAM • 512 GB/s
AMD
AmazonNeweggeBayPCPartPicker
AMD Radeon Pro W6900X
32 GB VRAM • 512 GB/s
AMD
AmazonNeweggeBayPCPartPicker
NVIDIA Jetson AGX Orin 32 GB
32 GB VRAM • 205 GB/s
NVIDIA
AmazonNeweggeBayPCPartPicker
AMD Radeon PRO W7800
32 GB VRAM • 576 GB/s
AMD
$2499
AmazonNeweggeBayPCPartPicker

Find the best GPU for Mixtral-8x7B

Build Hardware for Mixtral-8x7B

Model Card

View on HuggingFace

Mixtral 8x7B — groundbreaking open MoE. Runs at 13B speed with 47B total params.

▸ SPEC SHEET

Mixtral-8x7B — 46.7B MoE.

▸ SPECIFICATIONS
PARAMETERS
46.7B (13B active)
ARCHITECTURE
Mixture of Experts
CONTEXT LENGTH
32K tokens
CAPABILITIES
chat, coding
RELEASE DATE
2024-01-11
PROVIDER
Mistral AI
FAMILY
mistral
▸ VRAM REQUIREMENTS
QUANTBPWVRAMQUALITY
IQ3_XXS3.2519.5 GB82%
IQ3_XS3.520.9 GB84%
Q3_K_S3.6421.7 GB85%
IQ3_M3.7622.4 GB86%
Q3_K_M423.8 GB88%
Q3_K_L4.325.6 GB90%
IQ4_XS4.4626.5 GB92%
Q4_K_S4.6727.7 GB93%
Q4_K_M4.8929.0 GB94%
Q5_K_S5.5733.0 GB96%
Q5_K_M5.733.8 GB96%
Q6_K6.5638.8 GB97%
Q8_08.550.1 GB100%
FP161693.9 GB100%
§ 01BENCHMARK SCORES
MMLU-PRO29.6
MATH12.2
IFEval59.0
BBH37.1
GPQA9.5
MUSR16.7
GPQA Diamond29.2
LiveCodeBench6.6
MATH-50029.9
HLE4.5
AA Intelligence7.7
aa_scicode2.8
AIME0.0
§ 02RUN COMMAND

Run Mixtral-8x7B locally with Ollama — needs 29.0 GB VRAM at Q4_K_M:

$ollama run mixtral:8x7b
§ 03COMPATIBLE GPUs
30 @ Q4_K_M
NVIDIA RTX 5090
32 GB · 1792 GB/s
Apple M1 Max (32GB)
32 GB · 400 GB/s
Apple M2 Max (32GB)
32 GB · 400 GB/s
NVIDIA V100 SXM2 32GB
32 GB · 900 GB/s
Apple M2 Pro (32GB)
32 GB · 200 GB/s
Apple M4 (32GB)
32 GB · 120 GB/s
NVIDIA Tesla V100 DGXS 32 GB
32 GB · 897 GB/s
NVIDIA Tesla V100 PCIe 32 GB
32 GB · 897 GB/s
NVIDIA Tesla V100 SXM2 32 GB
32 GB · 898 GB/s
NVIDIA Tesla V100 SXM3 32 GB
32 GB · 981 GB/s
AMD Radeon Instinct MI60
32 GB · 1020 GB/s
NVIDIA Tesla V100S PCIe 32 GB
32 GB · 1130 GB/s
AMD Radeon Instinct MI100
32 GB · 1230 GB/s
NVIDIA RTX 5000 Ada Generation
32 GB · 576 GB/s
NVIDIA GeForce RTX 5090
32 GB · 1790 GB/s