Mistral
ChatCodingReasoningMulti-purpose46.7B
Chat

Mixtral 8x7B Instruct

Mixtral · Apache 2.0

Mixture of Experts: 46.7B total parameters, 12.9B active per token.

Mixture-of-Experts model: 46.7B total params but only ~12.9B active per token. Quality closer to a 13B dense model with inference speed to match. Needs more VRAM for the full weight set though.

Parameters
46.7B
Architecture
MoE (12.9B active)
Context
32,768 tokens
Released
2024-01-08
Engines
llama.cpp, ollama, vLLM

Parameters

46.7B

VRAM

31.4 GB

Context

32K

Formats

4

GPUs

19

Mixtral 8x7B Instruct (46.7B) requires 31.4 GB VRAM at recommended quality (Q5_K_M). On NVIDIA RTX PRO 6000 Blackwell, expect approximately 125 tok/s at Q5_K_M. For the best experience, High-End Home AI Server ($3,842) is recommended.

Source: OwnRig methodology

VRAM (Recommended)

31.4 GB

Quantization

Q5_K_M

File Size

28 GB

Max Context

32K tokens

Primary Use

Chat

Memory

VRAM Requirements

QualityQuantizationVRAMFile Size
recommendedQ5_K_M31.4 GB28 GB
efficientQ4_K_M26.2 GB23.4 GB
compressedQ3_K_M21 GB18.2 GB
compressedQ2_K16.4 GB14 GB
Scaling

Context Length Impact

KV cache VRAM at Q5_K_M quality. Longer context = more memory.

ContextKV CacheTotal VRAM
2K410 MB31.8 GBexceeds 24 GB
4K819 MB32.2 GBexceeds 24 GB
8K1.5 GB32.9 GBexceeds 24 GB
16K3.1 GB34.5 GBexceeds 24 GB
32K6.1 GB37.5 GBexceeds 24 GB

Compatible GPUs

19 devices
NVIDIA Grace Blackwell Ultra GB300Q5_K_M100 tok/sExcellent
NVIDIA RTX PRO 6000 BlackwellQ5_K_M125 tok/sExcellent
NVIDIA RTX PRO 6000 Blackwell Max-QQ5_K_M115 tok/sExcellent
Apple M4 Max (36GB Unified)Q4_K_M20 tok/sGood
Apple M4 Max (64GB Unified)Q5_K_M18 tok/sGood
NVIDIA GeForce RTX 4090Q3_K_M35 tok/sGood
AMD Radeon RX 7900 XTXQ3_K_M30 tok/sGood
AMD Radeon Pro W7900Q5_K_M19 tok/sGood
AMD Radeon RX 9070Q2_K4 tok/sMarginal
AMD Radeon RX 9060 XT 16GBQ2_K2 tok/sMarginal
Apple M3 Pro (18GB Unified)Q2_KNot viable
NVIDIA GeForce RTX 3080 10GBQ2_KNot viable
NVIDIA GeForce RTX 4060 8GBQ4_K_MNot viable
NVIDIA RTX 4060 Laptop (40-60W)Q4_K_MNot viable
NVIDIA RTX 4070 Laptop (80-115W)Q4_K_MNot viable
NVIDIA GeForce RTX 4070 Ti 12GBQ4_K_MNot viable
AMD Radeon RX 7600Q2_KNot viable
AMD Radeon RX 9060 XT 8GBQ2_KNot viable
NVIDIA GeForce RTX 5060 8GBQ4_K_MNot viable

Showing 19 of 19 entries

Hardware

Recommended Builds

Complete PC builds that can run Mixtral 8x7B Instruct.

FAQ

Frequently Asked Questions

How much VRAM does Mixtral 8x7B Instruct need?
Mixtral 8x7B Instruct requires 31.4 GB VRAM at recommended quality (Q5_K_M). At lower quality settings, it can fit in as little as 16.4 GB.
What is the best GPU for Mixtral 8x7B Instruct?
The NVIDIA RTX PRO 6000 Blackwell delivers the best performance for Mixtral 8x7B Instruct, achieving 125 tok/s at Q5_K_M with an excellent rating.
What quantization should I use for Mixtral 8x7B Instruct?
For the best quality, use Q5_K_M (31.4 GB VRAM). If your GPU has limited VRAM, Q2_K (16.4 GB) is the most efficient option with acceptable quality.
Is Mixtral 8x7B Instruct good for coding?
Mixtral 8x7B Instruct supports coding use cases. For the best coding experience, pair it with an embedding model for local RAG.
All models

Data confidence: verified. Source

VRAM requirements are calculated from model parameters and may vary by inference engine, context length, and batch size. Performance estimates are based on community benchmarks and should be verified for your specific configuration.Mixtral is a trademark of its respective owner. OwnRig is not affiliated with or endorsed by the model creator.