Outmake Models
Models

Kai Os Grug 12B

bartowski · July 2026

Get Hugging Face

A 12B chat model from bartowski that reads pictures as well as text.

Downloads
67K
Likes
3
Parameters
12B
Context
256K
Licence
other

Runs great on M4 · 16 GB

The Q4_K_S size from bartowski is the one to get: a 7.2 GB download that uses 7.6 GB of memory, and writes about 8.3 words a second.

Kai Os Grug 12B 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 bartowski/kai-os_Grug-12B-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.

SizeDownloadMemory at 8KGet
IQ2_S4.7 GB5.1 GBestimatedOpen
IQ2_M4.9 GB5.3 GBestimatedOpen
Q2_K5.1 GB5.4 GBestimatedOpen
IQ3_XXS5.1 GB5.5 GBestimatedOpen
Q2_K_L5.3 GB5.7 GBestimatedOpen
IQ3_XS5.5 GB5.9 GBestimatedOpen
Q3_K_S5.7 GB6.1 GBestimatedOpen
IQ3_M6.0 GB6.3 GBestimatedOpen
Q3_K_M6.3 GB6.7 GBestimatedOpen
Q3_K_L6.7 GB7.0 GBestimatedOpen
IQ4_XS6.8 GB7.1 GBestimatedOpen
Q3_K_XL6.9 GB7.3 GBestimatedOpen
IQ4_NL7.1 GB7.5 GBestimatedOpen
Q4_07.1 GB7.5 GBestimatedOpen
Q4_K_S7.2 GB7.5 GBestimatedOpen
Q4_K_M7.7 GB8.0 GBestimatedOpen
Q4_17.8 GB8.1 GBestimatedOpen
Q4_K_L7.9 GB8.3 GBestimatedOpen
Q5_K_S8.4 GB8.8 GBestimatedOpen
Q5_K_M8.8 GB9.1 GBestimatedOpen
Q5_K_L9.0 GB9.4 GBestimatedOpen
Q6_K10 GB11 GBestimatedOpen
Q6_K_L10 GB11 GBestimatedOpen
Q8_013 GB13 GBestimatedOpen
BF1624 GB24 GBestimatedOpen

Run It Anywhere

Kai Os Grug 12B is an open model, so any app that runs GGUF files can run it. These take the Q4_K_S size from bartowski straight from Hugging Face.

  • LM StudioMac, Windows, LinuxOpen
  • JanMac, Windows, LinuxOpen
  • MstyMac, Windows, LinuxOpen
  • OllamaMac, Windows, Linuxollama run hf.co/bartowski/kai-os_Grug-12B-GGUF:Q4_K_S
  • llama.cppMac, Windows, Linuxllama-server -hf bartowski/kai-os_Grug-12B-GGUF:Q4_K_S
  • Docker Model RunnerMac, Windows, Linuxdocker model run hf.co/bartowski/kai-os_Grug-12B-GGUF:Q4_K_S
On a PC Graphics Card
Video memoryLargest size that fitsDownloadMemory at 8K
6 GBIQ3_XS5.5 GB5.9 GB
8 GBQ4_K_S7.2 GB7.5 GB
10 GBQ5_K_L9.0 GB9.4 GB
11 GBQ6_K_L10 GB11 GB
12 GBQ6_K_L10 GB11 GB
16 GBQ8_013 GB13 GB
20 GBQ8_013 GB13 GB
24 GBQ8_013 GB13 GB
32 GBBF1624 GB24 GB
48 GBBF1624 GB24 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 GBQ4_K_SRuns great7.6 GB12
M6 · 24 GBQ6_K_LRuns great11 GB8.9
M6 · 32 GBQ8_0Runs great14 GB8.5
M5 · 16 GBQ4_K_SRuns great7.6 GB11
M5 · 24 GBQ6_K_LRuns great11 GB8.1
M5 · 32 GBQ8_0Runs great14 GB7.7
M5 Pro · 24 GBQ6_K_LRuns great11 GB16
M5 Pro · 48 GBQ8_0Runs great16 GB15
M5 Pro · 64 GBQ8_0Runs great16 GB15
M5 Max · 36 GBQ8_0Runs great16 GB22
M5 Max · 48 GBQ8_0Runs great16 GB29
M5 Max · 64 GBQ8_0Runs great16 GB29
M5 Max · 128 GBQ8_0Runs great16 GB29
M5 Ultra · 96 GBQ8_0Runs great16 GB54
M5 Ultra · 256 GBQ8_0Runs great16 GB54
M5 Ultra · 512 GBQ8_0Runs great16 GB54
M4 · 16 GBQ4_K_SRuns great7.6 GB8.3
M4 · 24 GBQ6_K_LRuns great11 GB6
M4 · 32 GBQ8_0Runs great14 GB5.8
M4 Pro · 24 GBQ6_K_LRuns great11 GB13
M4 Pro · 48 GBQ8_0Runs great16 GB12
M4 Pro · 64 GBQ8_0Runs great16 GB12
M4 Max · 36 GBQ8_0Runs great16 GB17
M4 Max · 48 GBQ8_0Runs great16 GB22
M4 Max · 64 GBQ8_0Runs great16 GB22
M4 Max · 96 GBQ8_0Runs great16 GB17
M4 Max · 128 GBQ8_0Runs great16 GB22
M3 · 8 GBIQ2_MRuns well5.3 GB9.7
M3 · 16 GBQ4_K_SRuns great7.6 GB7.1
M3 · 24 GBQ6_K_LRuns great11 GB5.1
M3 Pro · 18 GBQ4_K_LRuns great8.5 GB9.5
M3 Pro · 36 GBQ8_0Runs great16 GB7.2
M3 Max · 36 GBQ8_0Runs great16 GB14
M3 Max · 48 GBQ8_0Runs great16 GB17
M3 Max · 64 GBQ8_0Runs great16 GB17
M3 Max · 96 GBQ8_0Runs great16 GB14
M3 Max · 128 GBQ8_0Runs great16 GB17
M3 Ultra · 96 GBQ8_0Runs great16 GB30
M3 Ultra · 256 GBQ8_0Runs great16 GB30
M3 Ultra · 512 GBQ8_0Runs great16 GB30
M2 · 8 GBIQ2_MRuns well5.3 GB9.7
M2 · 16 GBQ4_K_SRuns great7.6 GB7.1
M2 · 24 GBQ6_K_LRuns great11 GB5.1
M2 Pro · 16 GBQ4_K_SRuns great7.6 GB13
M2 Pro · 32 GBQ8_0Runs great14 GB9.4
M2 Max · 32 GBQ8_0Runs great14 GB17
M2 Max · 64 GBQ8_0Runs great16 GB17
M2 Max · 96 GBQ8_0Runs great16 GB17
M2 Ultra · 64 GBQ8_0Runs great16 GB30
M2 Ultra · 128 GBQ8_0Runs great16 GB30
M2 Ultra · 192 GBQ8_0Runs great16 GB30
M1 · 8 GBIQ2_MRuns well5.3 GB6.5
M1 · 16 GBQ4_K_SRuns great7.6 GB4.8
M1 Pro · 16 GBQ4_K_SRuns great7.6 GB12
M1 Pro · 32 GBQ8_0Runs great14 GB8.9
M1 Max · 32 GBQ8_0Runs great14 GB16
M1 Max · 64 GBQ8_0Runs great16 GB16
M1 Ultra · 64 GBQ8_0Runs great16 GB26
M1 Ultra · 128 GBQ8_0Runs great16 GB26

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

Information

Maker
bartowski
Released
July 2026
Parameters
12B
Longest chat
256K tokens
Reads pictures
Yes
Licence
other
Downloads this month
66,720
Likes
3
Sizes
25, 4.7 to 24 GB
Kind
Maker's release

Badge for the model card

Shows on Kai Os Grug 12B'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