Outmake Models
Models

Mixtral 8x7B V0.1

Mistral AI · December 2023

Get Hugging Face

A 47B, 13B active chat model from Mistral AI.

Rating
2.3
Downloads
41K
Likes
1.1K
Parameters
47B, 13B active
Context
32K
Licence
apache-2.0

Too big for this Mac

Its smallest size needs 18 GB of memory, more than M4 · 16 GB can give it.

Ratings

2.3 out of 5, across people's blind votes on its answers.

Text
1197
Coding
1240

LM Arena ratings of October 28, 2026 (CC BY 4.0): people vote between two answers without knowing which model wrote which. The bar ends at 1488, the best any open model has. The Arena tests the full model; a small size on a Mac answers a little worse.

Mixtral 8x7B V0.1 runs well from a Mac with an M1 Pro and 32 GB of memory. 40 of 59 Mac configurations run it well.

Compare with

The nearest models in size.

Sizes

From TheBloke/Mixtral-8x7B-v0.1-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.

SizeDownloadMemory at 8KGet
Q2_K16 GB16 GBestimatedOpen
Q3_K_M20 GB21 GBestimatedOpen
Q4_026 GB27 GBestimatedOpen
Q4_K_M26 GB27 GBestimatedOpen
Q5_032 GB33 GBestimatedOpen
Q5_K_M32 GB33 GBestimatedOpen
Q6_K38 GB39 GBestimatedOpen
Q8_050 GB50 GBestimatedOpen

Run It Anywhere

Mixtral 8x7B V0.1 is an open model, so any app that runs GGUF files can run it. These take the Q2_K size from TheBloke straight from Hugging Face.

  • LM StudioMac, Windows, LinuxOpen
  • JanMac, Windows, LinuxOpen
  • MstyMac, Windows, LinuxOpen
  • OllamaMac, Windows, Linuxollama run hf.co/TheBloke/Mixtral-8x7B-v0.1-GGUF:Q2_K
  • llama.cppMac, Windows, Linuxllama-server -hf TheBloke/Mixtral-8x7B-v0.1-GGUF:Q2_K
  • Docker Model RunnerMac, Windows, Linuxdocker model run hf.co/TheBloke/Mixtral-8x7B-v0.1-GGUF:Q2_K
On a PC Graphics Card
Video memoryLargest size that fitsDownloadMemory at 8K
6 GBNone worth runningneeds 21 GB
8 GBNone worth runningneeds 21 GB
10 GBNone worth runningneeds 21 GB
11 GBNone worth runningneeds 21 GB
12 GBNone worth runningneeds 21 GB
16 GBNone worth runningneeds 21 GB
20 GBNone worth runningneeds 21 GB
24 GBQ3_K_M20 GB21 GB
32 GBQ4_K_M26 GB27 GB
48 GBQ6_K38 GB39 GB

The largest size, of those that keep three bits a weight or more, whose memory at an 8K chat is under 92% of the card's; the rest is the desktop's. Estimated from the files, the same way as for a Mac; speed on a PC is not estimated yet. A size that doesn't fit the card still runs, slower, with part of it in ordinary memory.

On every Mac
MacSizeFitMemoryWrites
M6 · 16 GBQ2_KToo big18 GB
M6 · 24 GBQ2_KTight fit19 GB7.5
M6 · 32 GBQ3_K_MRuns well21 GB6.8
M5 · 16 GBQ2_KToo big18 GB
M5 · 24 GBQ2_KTight fit19 GB6.8
M5 · 32 GBQ3_K_MRuns well21 GB6.2
M5 Pro · 24 GBQ2_KTight fit19 GB13
M5 Pro · 48 GBQ4_K_MRuns well31 GB10
M5 Pro · 64 GBQ4_K_MRuns great30 GB10
M5 Max · 36 GBQ3_K_MRuns well24 GB17
M5 Max · 48 GBQ4_K_MRuns well31 GB19
M5 Max · 64 GBQ4_K_MRuns great30 GB19
M5 Max · 128 GBQ8_0Runs great52 GB16
M5 Ultra · 96 GBQ6_KRuns great41 GB32
M5 Ultra · 256 GBQ8_0Runs great52 GB30
M5 Ultra · 512 GBQ8_0Runs great52 GB30
M4 · 16 GBQ2_KToo big18 GB
M4 · 24 GBQ2_KTight fit19 GB5.2
M4 · 32 GBQ3_K_MRuns well21 GB4.8
M4 Pro · 24 GBQ2_KTight fit19 GB11
M4 Pro · 48 GBQ4_K_MRuns well31 GB8.5
M4 Pro · 64 GBQ4_K_MRuns great30 GB8.5
M4 Max · 36 GBQ3_K_MRuns well24 GB14
M4 Max · 48 GBQ4_K_MRuns well31 GB16
M4 Max · 64 GBQ4_K_MRuns great30 GB16
M4 Max · 96 GBQ6_KRuns great41 GB10
M4 Max · 128 GBQ8_0Runs great52 GB13
M3 · 8 GBQ2_KToo big18 GB
M3 · 16 GBQ2_KToo big18 GB
M3 · 24 GBQ2_KTight fit19 GB4.4
M3 Pro · 18 GBQ2_KToo big18 GB
M3 Pro · 36 GBQ3_K_MRuns well24 GB5.7
M3 Max · 36 GBQ3_K_MRuns well24 GB11
M3 Max · 48 GBQ4_K_MRuns well31 GB12
M3 Max · 64 GBQ4_K_MRuns great30 GB12
M3 Max · 96 GBQ6_KRuns great41 GB7.8
M3 Max · 128 GBQ8_0Runs great52 GB9.8
M3 Ultra · 96 GBQ6_KRuns great41 GB19
M3 Ultra · 256 GBQ8_0Runs great52 GB18
M3 Ultra · 512 GBQ8_0Runs great52 GB18
M2 · 8 GBQ2_KToo big18 GB
M2 · 16 GBQ2_KToo big18 GB
M2 · 24 GBQ2_KTight fit19 GB4.4
M2 Pro · 16 GBQ2_KToo big18 GB
M2 Pro · 32 GBQ3_K_MRuns well21 GB7.8
M2 Max · 32 GBQ3_K_MRuns well21 GB15
M2 Max · 64 GBQ4_K_MRuns great30 GB12
M2 Max · 96 GBQ6_KRuns great41 GB10
M2 Ultra · 64 GBQ4_K_MRuns great30 GB22
M2 Ultra · 128 GBQ8_0Runs great52 GB18
M2 Ultra · 192 GBQ8_0Runs great52 GB18
M1 · 8 GBQ2_KToo big18 GB
M1 · 16 GBQ2_KToo big18 GB
M1 Pro · 16 GBQ2_KToo big18 GB
M1 Pro · 32 GBQ3_K_MRuns well21 GB7.5
M1 Max · 32 GBQ3_K_MRuns well21 GB13
M1 Max · 64 GBQ4_K_MRuns great30 GB11
M1 Ultra · 64 GBQ4_K_MRuns great30 GB19
M1 Ultra · 128 GBQ8_0Runs great52 GB16

Writes is words a second, estimated from the Mac's memory speed and the model's size; how, and how wrong.

Packaged by

3 repositories on Hugging Face carry this model for llama.cpp. Outmake reads them all as one model.

Information

Maker
Mistral AI
Released
December 2023
Parameters
47B, 13B active
Longest chat
32K tokens
Reads pictures
No
Licence
apache-2.0
Downloads this month
40,837
Likes
1,097
Sizes
8, 16 to 50 GB
Kind
Maker's release

Badge for the model card

Shows on Mixtral 8x7B V0.1's Hugging Face card which Macs run it well, linked to this page. It updates every morning.

Runs on Mac badge

Files, downloads and likes read from Hugging Face on November 5, 2026 and refreshed every morning. Memory and speed are estimates until someone running Outmake measures this model on that Mac.

Your Computer

Every model is judged for this Mac. Both are under About This Mac, in the Apple menu.

Every Mac · Every graphics card

Civitai

Open in OutmakeHugging Face

New to Outmake? Download the free beta