Outmake Models
Models

EsoTest GGUFs

Esobold · May 2026

Get Hugging Face

A 31B chat model from Esobold.

Downloads
51K
Parameters
31B
Context
256K

Too big for this Mac

Its smallest size needs 22 GB of memory, more than M4 · 16 GB can give it.

EsoTest GGUFs 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 Esobold/EsoTest_GGUFs on Hugging Face. A smaller size is a smaller download and a little less accurate.

SizeDownloadMemory at 8KGet
IQ4_XS17 GB17 GBestimatedOpen
Q4_K_S18 GB18 GBestimatedOpen
fortunajuvat-q4km19 GB19 GBestimatedOpen
tworomes-q4km19 GB19 GBestimatedOpen
mistermarks-q4km19 GB19 GBestimatedOpen
mysterygizmo-q4km19 GB19 GBestimatedOpen
Q4_K_M19 GB19 GBestimatedOpen
leisurelylion-q4km19 GB19 GBestimatedOpen
leisurelyocelot-q4km19 GB19 GBestimatedOpen
mistersalaryman-q4km19 GB19 GBestimatedOpen
teamworksmilodon-q4km19 GB19 GBestimatedOpen
TestWL-Merged-Q4KM19 GB20 GBestimatedOpen
Mentlegen-Q4KM19 GB20 GBestimatedOpen
Q5_K_M22 GB22 GBestimatedOpen

Run It Anywhere

EsoTest GGUFs is an open model, so any app that runs GGUF files can run it. These take the IQ4_XS size from Esobold straight from Hugging Face.

  • LM StudioMac, Windows, LinuxOpen
  • JanMac, Windows, LinuxOpen
  • MstyMac, Windows, LinuxOpen
  • OllamaMac, Windows, Linuxollama run hf.co/Esobold/EsoTest_GGUFs:IQ4_XS
  • llama.cppMac, Windows, Linuxllama-server -hf Esobold/EsoTest_GGUFs:IQ4_XS
  • Docker Model RunnerMac, Windows, Linuxdocker model run hf.co/Esobold/EsoTest_GGUFs:IQ4_XS
On a PC Graphics Card
Video memoryLargest size that fitsDownloadMemory at 8K
6 GBNone worth runningneeds 17 GB
8 GBNone worth runningneeds 17 GB
10 GBNone worth runningneeds 17 GB
11 GBNone worth runningneeds 17 GB
12 GBNone worth runningneeds 17 GB
16 GBNone worth runningneeds 17 GB
20 GBMentlegen-Q4KM19 GB20 GB
24 GBQ5_K_M22 GB22 GB
32 GBQ5_K_M22 GB22 GB
48 GBQ5_K_M22 GB22 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 GBIQ4_XSToo big22 GB
M6 · 24 GBQ4_K_STight fit19 GB5
M6 · 32 GBQ4_K_MRuns well20 GB4.8
M5 · 16 GBIQ4_XSToo big22 GB
M5 · 24 GBQ4_K_STight fit19 GB4.6
M5 · 32 GBQ4_K_MRuns well20 GB4.4
M5 Pro · 24 GBQ4_K_STight fit19 GB9.1
M5 Pro · 48 GBQ5_K_MRuns great23 GB7.5
M5 Pro · 64 GBQ5_K_MRuns great27 GB7.5
M5 Max · 36 GBIQ4_XSRuns great17 GB14
M5 Max · 48 GBQ5_K_MRuns great23 GB15
M5 Max · 64 GBQ5_K_MRuns great27 GB15
M5 Max · 128 GBQ5_K_MRuns great27 GB15
M5 Ultra · 96 GBQ5_K_MRuns great27 GB29
M5 Ultra · 256 GBQ5_K_MRuns great27 GB29
M5 Ultra · 512 GBQ5_K_MRuns great27 GB29
M4 · 16 GBIQ4_XSToo big22 GB
M4 · 24 GBQ4_K_STight fit19 GB3.7
M4 · 32 GBQ4_K_MRuns well20 GB3.5
M4 Pro · 24 GBQ4_K_STight fit19 GB8.1
M4 Pro · 48 GBQ5_K_MRuns great23 GB6.7
M4 Pro · 64 GBQ5_K_MRuns great27 GB6.7
M4 Max · 36 GBIQ4_XSRuns great17 GB12
M4 Max · 48 GBQ5_K_MRuns great23 GB13
M4 Max · 64 GBQ5_K_MRuns great27 GB13
M4 Max · 96 GBQ5_K_MRuns great27 GB9.8
M4 Max · 128 GBQ5_K_MRuns great27 GB13
M3 · 8 GBIQ4_XSToo big22 GB
M3 · 16 GBIQ4_XSToo big22 GB
M3 · 24 GBQ4_K_STight fit19 GB3.1
M3 Pro · 18 GBIQ4_XSToo big22 GB
M3 Pro · 36 GBIQ4_XSRuns great17 GB4.8
M3 Max · 36 GBIQ4_XSRuns great17 GB9.4
M3 Max · 48 GBQ5_K_MRuns great23 GB9.7
M3 Max · 64 GBQ5_K_MRuns great27 GB9.7
M3 Max · 96 GBQ5_K_MRuns great27 GB7.4
M3 Max · 128 GBQ5_K_MRuns great27 GB9.7
M3 Ultra · 96 GBQ5_K_MRuns great27 GB18
M3 Ultra · 256 GBQ5_K_MRuns great27 GB18
M3 Ultra · 512 GBQ5_K_MRuns great27 GB18
M2 · 8 GBIQ4_XSToo big22 GB
M2 · 16 GBIQ4_XSToo big22 GB
M2 · 24 GBQ4_K_STight fit19 GB3.1
M2 Pro · 16 GBIQ4_XSToo big22 GB
M2 Pro · 32 GBQ4_K_MRuns well20 GB5.8
M2 Max · 32 GBQ4_K_MRuns well20 GB11
M2 Max · 64 GBQ5_K_MRuns great27 GB9.7
M2 Max · 96 GBQ5_K_MRuns great27 GB9.7
M2 Ultra · 64 GBQ5_K_MRuns great27 GB18
M2 Ultra · 128 GBQ5_K_MRuns great27 GB18
M2 Ultra · 192 GBQ5_K_MRuns great27 GB18
M1 · 8 GBIQ4_XSToo big22 GB
M1 · 16 GBIQ4_XSToo big22 GB
M1 Pro · 16 GBIQ4_XSToo big22 GB
M1 Pro · 32 GBQ4_K_MRuns well20 GB5.6
M1 Max · 32 GBQ4_K_MRuns well20 GB11
M1 Max · 64 GBQ5_K_MRuns great27 GB9.3
M1 Ultra · 64 GBQ5_K_MRuns great27 GB17
M1 Ultra · 128 GBQ5_K_MRuns great27 GB17

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

Information

Maker
Esobold
Released
May 2026
Parameters
31B
Longest chat
256K tokens
Reads pictures
No
Licence
Not stated
Downloads this month
51,191
Sizes
14, 17 to 22 GB
Kind
Maker's release

Badge for the model card

Shows on EsoTest GGUFs'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