Outmake Models
Models

Gemma 4 E4B Qat Mobile

unsloth · June 2026

Get Hugging Face

A 7.5B chat model from unsloth that reads pictures as well as text.

Downloads
52K
Likes
35
Parameters
7.5B
Context
128K
Licence
apache-2.0

Runs great on M4 · 16 GB

The UD-Q2_K_XL size from unsloth is the one to get: a 3.2 GB download that uses 5.7 GB of memory, and writes about 14 words a second.

Gemma 4 E4B Qat Mobile 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 unsloth/gemma-4-E4B-it-qat-mobile-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.

SizeDownloadMemory at 8KGet
UD-Q2_K_XL3.2 GB3.5 GBestimatedOpen

Run It Anywhere

Gemma 4 E4B Qat Mobile is an open model, so any app that runs GGUF files can run it. These take the UD-Q2_K_XL size from unsloth straight from Hugging Face.

  • LM StudioMac, Windows, LinuxOpen
  • JanMac, Windows, LinuxOpen
  • MstyMac, Windows, LinuxOpen
  • OllamaMac, Windows, Linuxollama run hf.co/unsloth/gemma-4-E4B-it-qat-mobile-GGUF:UD-Q2_K_XL
  • llama.cppMac, Windows, Linuxllama-server -hf unsloth/gemma-4-E4B-it-qat-mobile-GGUF:UD-Q2_K_XL
  • Docker Model RunnerMac, Windows, Linuxdocker model run hf.co/unsloth/gemma-4-E4B-it-qat-mobile-GGUF:UD-Q2_K_XL
On a PC Graphics Card
Video memoryLargest size that fitsDownloadMemory at 8K
6 GBUD-Q2_K_XL3.2 GB3.5 GB
8 GBUD-Q2_K_XL3.2 GB3.5 GB
10 GBUD-Q2_K_XL3.2 GB3.5 GB
11 GBUD-Q2_K_XL3.2 GB3.5 GB
12 GBUD-Q2_K_XL3.2 GB3.5 GB
16 GBUD-Q2_K_XL3.2 GB3.5 GB
20 GBUD-Q2_K_XL3.2 GB3.5 GB
24 GBUD-Q2_K_XL3.2 GB3.5 GB
32 GBUD-Q2_K_XL3.2 GB3.5 GB
48 GBUD-Q2_K_XL3.2 GB3.5 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 GBUD-Q2_K_XLRuns great5.7 GB21
M6 · 24 GBUD-Q2_K_XLRuns great5.7 GB21
M6 · 32 GBUD-Q2_K_XLRuns great5.7 GB21
M5 · 16 GBUD-Q2_K_XLRuns great5.7 GB20
M5 · 24 GBUD-Q2_K_XLRuns great5.7 GB20
M5 · 32 GBUD-Q2_K_XLRuns great5.7 GB20
M5 Pro · 24 GBUD-Q2_K_XLRuns great5.7 GB38
M5 Pro · 48 GBUD-Q2_K_XLRuns great5.7 GB38
M5 Pro · 64 GBUD-Q2_K_XLRuns great5.7 GB38
M5 Max · 36 GBUD-Q2_K_XLRuns great5.7 GB54
M5 Max · 48 GBUD-Q2_K_XLRuns great5.7 GB69
M5 Max · 64 GBUD-Q2_K_XLRuns great5.7 GB69
M5 Max · 128 GBUD-Q2_K_XLRuns great5.7 GB69
M5 Ultra · 96 GBUD-Q2_K_XLRuns great5.7 GB117
M5 Ultra · 256 GBUD-Q2_K_XLRuns great5.7 GB117
M5 Ultra · 512 GBUD-Q2_K_XLRuns great5.7 GB117
M4 · 16 GBUD-Q2_K_XLRuns great5.7 GB14
M4 · 24 GBUD-Q2_K_XLRuns great5.7 GB14
M4 · 32 GBUD-Q2_K_XLRuns great5.7 GB14
M4 Pro · 24 GBUD-Q2_K_XLRuns great5.7 GB28
M4 Pro · 48 GBUD-Q2_K_XLRuns great5.7 GB28
M4 Pro · 64 GBUD-Q2_K_XLRuns great5.7 GB28
M4 Max · 36 GBUD-Q2_K_XLRuns great5.7 GB37
M4 Max · 48 GBUD-Q2_K_XLRuns great5.7 GB43
M4 Max · 64 GBUD-Q2_K_XLRuns great5.7 GB43
M4 Max · 96 GBUD-Q2_K_XLRuns great5.7 GB37
M4 Max · 128 GBUD-Q2_K_XLRuns great5.7 GB43
M3 · 8 GBUD-Q2_K_XLRuns great3.6 GB13
M3 · 16 GBUD-Q2_K_XLRuns great5.7 GB13
M3 · 24 GBUD-Q2_K_XLRuns great5.7 GB13
M3 Pro · 18 GBUD-Q2_K_XLRuns great5.7 GB18
M3 Pro · 36 GBUD-Q2_K_XLRuns great5.7 GB18
M3 Max · 36 GBUD-Q2_K_XLRuns great5.7 GB31
M3 Max · 48 GBUD-Q2_K_XLRuns great5.7 GB38
M3 Max · 64 GBUD-Q2_K_XLRuns great5.7 GB38
M3 Max · 96 GBUD-Q2_K_XLRuns great5.7 GB31
M3 Max · 128 GBUD-Q2_K_XLRuns great5.7 GB38
M3 Ultra · 96 GBUD-Q2_K_XLRuns great5.7 GB58
M3 Ultra · 256 GBUD-Q2_K_XLRuns great5.7 GB58
M3 Ultra · 512 GBUD-Q2_K_XLRuns great5.7 GB58
M2 · 8 GBUD-Q2_K_XLRuns great3.6 GB13
M2 · 16 GBUD-Q2_K_XLRuns great5.7 GB13
M2 · 24 GBUD-Q2_K_XLRuns great5.7 GB13
M2 Pro · 16 GBUD-Q2_K_XLRuns great5.7 GB23
M2 Pro · 32 GBUD-Q2_K_XLRuns great5.7 GB23
M2 Max · 32 GBUD-Q2_K_XLRuns great5.7 GB38
M2 Max · 64 GBUD-Q2_K_XLRuns great5.7 GB38
M2 Max · 96 GBUD-Q2_K_XLRuns great5.7 GB38
M2 Ultra · 64 GBUD-Q2_K_XLRuns great5.7 GB57
M2 Ultra · 128 GBUD-Q2_K_XLRuns great5.7 GB57
M2 Ultra · 192 GBUD-Q2_K_XLRuns great5.7 GB57
M1 · 8 GBUD-Q2_K_XLRuns great3.6 GB8.4
M1 · 16 GBUD-Q2_K_XLRuns great5.7 GB8.4
M1 Pro · 16 GBUD-Q2_K_XLRuns great5.7 GB20
M1 Pro · 32 GBUD-Q2_K_XLRuns great5.7 GB20
M1 Max · 32 GBUD-Q2_K_XLRuns great5.7 GB31
M1 Max · 64 GBUD-Q2_K_XLRuns great5.7 GB31
M1 Ultra · 64 GBUD-Q2_K_XLRuns great5.7 GB43
M1 Ultra · 128 GBUD-Q2_K_XLRuns great5.7 GB43

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

Information

Maker
unsloth
Released
June 2026
Parameters
7.5B
Longest chat
128K tokens
Reads pictures
Yes
Licence
apache-2.0
Downloads this month
52,418
Likes
35
Sizes
1, 3.2 to 3.2 GB
Kind
Maker's release

Badge for the model card

Shows on Gemma 4 E4B Qat Mobile'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