v2.2 · 2026-06-12

Mixtral 8x7B Instruct v0.1

mixtral-8x7b-instruct-v0-1

TEXT-CHAT

Mixtral 8x7B Instruct v0.1 is a 46.7B text chat model profile for local AI planning. This page records provider, license, context, quantization, hardware-fit estimates, setup hints, source links, and caveats so readers do not choose a model by name alone.

PROVIDER

Mistral AI

FAMILY

mixtral

MODEL TYPE

text-chat

PARAMETERS

46.7B (12.9B active)

MODALITIES

text

ARCHITECTURE

decoder-only sparse mixture-of-experts Transformer with 8 experts and top-2 expert routing

CONTEXT WINDOW

32,768 tokens

TRAINING TOKENS

—

RELEASE DATE

2023-12-11

LICENSE & LINKS

Apache-2.0license text

MODEL CARD

huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1

HUGGING FACE

mistralai/Mixtral-8x7B-Instruct-v0.1

GGUF REPOSITORIES

TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF community conversion

Community GGUF conversion with Q4_K_M, Q5_K_M and Q8_0 file-size table and RAM estimates.

SETUP HINTS

OLLAMA

ollama run mixtral:8x7b

LM STUDIO

Use TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF and select Q4_K_M only on machines with enough memory.

LLAMA.CPP

Download the Q4_K_M GGUF from TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF and run llama-server with a context length appropriate to available memory.

QUANTIZATION FILE SIZES (GGUF)

Q4_K_M

26.44 GB

Q5_K_M

32.23 GB

Q8_0

49.62 GB

Quantization note: Q4_K_M

RAM / VRAM ESTIMATES

MIN RAM

30 GB

COMFORTABLE RAM

48 GB

MIN VRAM

30 GB

COMFORTABLE VRAM

48 GB

These are conservative local-inference estimates, not official hardware requirements.

HARDWARE FIT

CPU only (no GPU)

limited

8 GB RAM

16 GB RAM

32 GB RAM

limited

8 GB VRAM

12 GB VRAM

24 GB VRAM

partial_offload_only

Apple Silicon (unified memory)

limited_on_32gb_unified_memory

Hardware fit values are conservative local-inference estimates based on GGUF size plus runtime and KV-cache overhead. Actual requirements depend on context length, quantization, runtime, GPU offload, and other running apps.

BEST FOR

·Apache-2.0 MoE local model

·strong classic open-weight chat baseline

·systems that benefit from sparse active parameters

·benchmarking against newer dense local models

AVOID IF

·you have less than 32 GB RAM

·you need easy 24 GB GPU full-offload deployment

·you need a current-generation small model with simpler deployment

CAVEATS

·RAM and VRAM estimates are conservative local-inference estimates based on GGUF file size plus runtime and KV-cache overhead; TheBloke's table reports 28.94 GB max RAM for Q4_K_M before additional deployment margin.

·Total and active parameter counts are MoE-specific; the catalog stores total parameters separately from approximate active parameters per token.

·The fetched sources did not provide a verified exhaustive language list, so languages is empty.

·Explicit tool-call support was not independently verified in the fetched reliable sources; supportsTools is null.

SOURCE URLS