Outmake Models
Models

Mistral 7B V0.1

Mistral AI · September 2023

Get Hugging Face

A 7.2B chat model from Mistral AI.

Downloads
60K
Likes
895
Parameters
7.2B
Context
32K
Licence
apache-2.0

Runs great on M4 · 16 GB

The Q6_K size from TheBloke is the one to get: a 5.9 GB download that uses 7.3 GB of memory, and writes about 6.7 words a second.

Mistral 7B V0.1 runs well from a Mac with an M1 and 8 GB of memory. 59 of 59 Mac configurations run it well.

Compare with

The nearest models in size.

Sizes

From TheBloke/Mistral-7B-v0.1-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.

SizeDownloadMemory at 8KGet
Q2_K3.1 GB3.8 GBestimatedOpen
Q3_K_S3.2 GB3.9 GBestimatedOpen
Q3_K_M3.5 GB4.2 GBestimatedOpen
Q3_K_L3.8 GB4.6 GBestimatedOpen
Q4_04.1 GB4.8 GBestimatedOpen
Q4_K_S4.1 GB4.9 GBestimatedOpen
Q4_K_M4.4 GB5.1 GBestimatedOpen
Q5_05.0 GB5.7 GBestimatedOpen
Q5_K_S5.0 GB5.7 GBestimatedOpen
Q5_K_M5.1 GB5.9 GBestimatedOpen
Q6_K5.9 GB6.7 GBestimatedOpen
Q8_07.7 GB8.4 GBestimatedOpen

Run It Anywhere

Mistral 7B V0.1 is an open model, so any app that runs GGUF files can run it. These take the Q6_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/Mistral-7B-v0.1-GGUF:Q6_K
  • llama.cppMac, Windows, Linuxllama-server -hf TheBloke/Mistral-7B-v0.1-GGUF:Q6_K
  • Docker Model RunnerMac, Windows, Linuxdocker model run hf.co/TheBloke/Mistral-7B-v0.1-GGUF:Q6_K
On a PC Graphics Card
Video memoryLargest size that fitsDownloadMemory at 8K
6 GBQ5_K_M5.1 GB5.9 GB
8 GBQ6_K5.9 GB6.7 GB
10 GBQ8_07.7 GB8.4 GB
11 GBQ8_07.7 GB8.4 GB
12 GBQ8_07.7 GB8.4 GB
16 GBQ8_07.7 GB8.4 GB
20 GBQ8_07.7 GB8.4 GB
24 GBQ8_07.7 GB8.4 GB
32 GBQ8_07.7 GB8.4 GB
48 GBQ8_07.7 GB8.4 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 GBQ6_KRuns great7.3 GB9.8
M6 · 24 GBQ8_0Runs great10 GB9.5
M6 · 32 GBQ8_0Runs great10 GB9.5
M5 · 16 GBQ6_KRuns great7.3 GB8.9
M5 · 24 GBQ8_0Runs great10 GB8.6
M5 · 32 GBQ8_0Runs great10 GB8.6
M5 Pro · 24 GBQ8_0Runs great10 GB17
M5 Pro · 48 GBQ8_0Runs great10 GB17
M5 Pro · 64 GBQ8_0Runs great10 GB17
M5 Max · 36 GBQ8_0Runs great10 GB25
M5 Max · 48 GBQ8_0Runs great10 GB33
M5 Max · 64 GBQ8_0Runs great10 GB33
M5 Max · 128 GBQ8_0Runs great10 GB33
M5 Ultra · 96 GBQ8_0Runs great10 GB63
M5 Ultra · 256 GBQ8_0Runs great10 GB63
M5 Ultra · 512 GBQ8_0Runs great10 GB63
M4 · 16 GBQ6_KRuns great7.3 GB6.7
M4 · 24 GBQ8_0Runs great10 GB6.5
M4 · 32 GBQ8_0Runs great10 GB6.5
M4 Pro · 24 GBQ8_0Runs great10 GB14
M4 Pro · 48 GBQ8_0Runs great10 GB14
M4 Pro · 64 GBQ8_0Runs great10 GB14
M4 Max · 36 GBQ8_0Runs great10 GB20
M4 Max · 48 GBQ8_0Runs great10 GB26
M4 Max · 64 GBQ8_0Runs great10 GB26
M4 Max · 96 GBQ8_0Runs great10 GB20
M4 Max · 128 GBQ8_0Runs great10 GB26
M3 · 8 GBQ4_K_MRuns well5.1 GB6.6
M3 · 16 GBQ6_KRuns great7.3 GB5.7
M3 · 24 GBQ8_0Runs great10 GB5.5
M3 Pro · 18 GBQ8_0Runs great8.4 GB8.1
M3 Pro · 36 GBQ8_0Runs great10 GB8.1
M3 Max · 36 GBQ8_0Runs great10 GB16
M3 Max · 48 GBQ8_0Runs great10 GB20
M3 Max · 64 GBQ8_0Runs great10 GB20
M3 Max · 96 GBQ8_0Runs great10 GB16
M3 Max · 128 GBQ8_0Runs great10 GB20
M3 Ultra · 96 GBQ8_0Runs great10 GB36
M3 Ultra · 256 GBQ8_0Runs great10 GB36
M3 Ultra · 512 GBQ8_0Runs great10 GB36
M2 · 8 GBQ4_K_MRuns well5.1 GB6.6
M2 · 16 GBQ6_KRuns great7.3 GB5.7
M2 · 24 GBQ8_0Runs great10 GB5.5
M2 Pro · 16 GBQ6_KRuns great7.3 GB11
M2 Pro · 32 GBQ8_0Runs great10 GB11
M2 Max · 32 GBQ8_0Runs great10 GB20
M2 Max · 64 GBQ8_0Runs great10 GB20
M2 Max · 96 GBQ8_0Runs great10 GB20
M2 Ultra · 64 GBQ8_0Runs great10 GB36
M2 Ultra · 128 GBQ8_0Runs great10 GB36
M2 Ultra · 192 GBQ8_0Runs great10 GB36
M1 · 8 GBQ4_K_MRuns well5.1 GB4.5
M1 · 16 GBQ6_KRuns great7.3 GB3.8
M1 Pro · 16 GBQ6_KRuns great7.3 GB10
M1 Pro · 32 GBQ8_0Runs great10 GB10
M1 Max · 32 GBQ8_0Runs great10 GB19
M1 Max · 64 GBQ8_0Runs great10 GB19
M1 Ultra · 64 GBQ8_0Runs great10 GB32
M1 Ultra · 128 GBQ8_0Runs great10 GB32

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

Packaged by

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

Information

Maker
Mistral AI
Released
September 2023
Parameters
7.2B
Longest chat
32K tokens
Reads pictures
No
Licence
apache-2.0
Downloads this month
59,596
Likes
895
Sizes
12, 3.1 to 7.7 GB
Kind
Maker's release

Badge for the model card

Shows on Mistral 7B 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