Outmake Models
Models

Artemis 31B V1.2

TheDrummer · September 2026

Get Hugging Face

A 31B chat model from TheDrummer that reads pictures as well as text.

Downloads
92K
Likes
45
Parameters
31B
Context
256K

Runs well on M4 · 16 GB

The IQ2_XS size from bartowski is the one to get: a 9.6 GB download that uses 11 GB of memory, and writes about 5.3 words a second.

Artemis 31B V1.2 runs well from a Mac with an M1 and 16 GB of memory. 56 of 59 Mac configurations run it well.

Compare with

The nearest models in size.

Sizes

From bartowski/TheDrummer_Artemis-31B-v1.2-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.

SizeDownloadMemory at 8KGet
IQ2_XXS9.2 GB10 GBestimatedOpen
IQ2_XS9.6 GB11 GBestimatedOpen
IQ2_S10 GB11 GBestimatedOpen
IQ2_M11 GB12 GBestimatedOpen
Q2_K12 GB13 GBestimatedOpen
IQ3_XXS13 GB14 GBestimatedOpen
Q3_K_S14 GB15 GBestimatedOpen
IQ3_XS14 GB15 GBestimatedOpen
Q3_K_M15 GB16 GBestimatedOpen
Q3_K_L16 GB17 GBestimatedOpen
IQ3_M16 GB17 GBestimatedOpen
IQ4_XS17 GB18 GBestimatedOpen
Q4_018 GB19 GBestimatedOpen
Q4_K_S18 GB19 GBestimatedOpen
IQ4_NL19 GB20 GBestimatedOpen
Q4_K_M20 GB20 GBestimatedOpen
Q4_120 GB21 GBestimatedOpen
Q4_K_L21 GB22 GBestimatedOpen
Q5_K_S22 GB23 GBestimatedOpen
Q5_K_M24 GB24 GBestimatedOpen
Q6_K_S26 GB27 GBestimatedOpen
Q6_K27 GB28 GBestimatedOpen
Q6_K_L28 GB29 GBestimatedOpen
Q8_033 GB34 GBestimatedOpen
BF1661 GB62 GBestimatedOpen

Run It Anywhere

Artemis 31B V1.2 is an open model, so any app that runs GGUF files can run it. These take the IQ2_XS size from bartowski straight from Hugging Face.

  • LM StudioMac, Windows, LinuxOpen
  • JanMac, Windows, LinuxOpen
  • MstyMac, Windows, LinuxOpen
  • OllamaMac, Windows, Linuxollama run hf.co/bartowski/TheDrummer_Artemis-31B-v1.2-GGUF:IQ2_XS
  • llama.cppMac, Windows, Linuxllama-server -hf bartowski/TheDrummer_Artemis-31B-v1.2-GGUF:IQ2_XS
  • Docker Model RunnerMac, Windows, Linuxdocker model run hf.co/bartowski/TheDrummer_Artemis-31B-v1.2-GGUF:IQ2_XS
On a PC Graphics Card
Video memoryLargest size that fitsDownloadMemory at 8K
6 GBNone worth runningneeds 14 GB
8 GBNone worth runningneeds 14 GB
10 GBNone worth runningneeds 14 GB
11 GBNone worth runningneeds 14 GB
12 GBNone worth runningneeds 14 GB
16 GBQ3_K_M15 GB16 GB
20 GBQ4_K_S18 GB19 GB
24 GBQ5_K_S22 GB23 GB
32 GBQ6_K_L28 GB29 GB
48 GBQ8_033 GB34 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 GBIQ2_XSRuns well11 GB7.5
M6 · 24 GBQ3_K_MRuns well16 GB5.4
M6 · 32 GBQ4_1Runs well21 GB4.8
M5 · 16 GBIQ2_XSRuns well11 GB6.8
M5 · 24 GBQ3_K_MRuns well16 GB4.9
M5 · 32 GBQ4_1Runs well21 GB4.3
M5 Pro · 24 GBQ3_K_MRuns well16 GB9.6
M5 Pro · 48 GBQ5_K_SRuns great23 GB6.9
M5 Pro · 64 GBQ6_K_LRuns great31 GB5.8
M5 Max · 36 GBIQ3_MRuns great17 GB13
M5 Max · 48 GBQ5_K_SRuns great23 GB13
M5 Max · 64 GBQ6_K_LRuns great31 GB11
M5 Max · 128 GBQ8_0Runs great47 GB11
M5 Ultra · 96 GBQ8_0Runs great40 GB22
M5 Ultra · 256 GBQ8_0Runs great47 GB22
M5 Ultra · 512 GBQ8_0Runs great47 GB22
M4 · 16 GBIQ2_XSRuns well11 GB5.3
M4 · 24 GBQ3_K_MRuns well16 GB3.8
M4 · 32 GBQ4_1Runs well21 GB3.4
M4 Pro · 24 GBQ3_K_MRuns well16 GB8.1
M4 Pro · 48 GBQ5_K_SRuns great23 GB6
M4 Pro · 64 GBQ6_K_LRuns great31 GB4.9
M4 Max · 36 GBIQ3_MRuns great17 GB11
M4 Max · 48 GBQ5_K_SRuns great23 GB11
M4 Max · 64 GBQ6_K_LRuns great31 GB9.1
M4 Max · 96 GBQ8_0Runs great40 GB7.1
M4 Max · 128 GBQ8_0Runs great47 GB9.2
M3 · 8 GBIQ1_SToo big21 GB
M3 · 16 GBIQ2_XSRuns well11 GB4.5
M3 · 24 GBQ3_K_MRuns well16 GB3.2
M3 Pro · 18 GBIQ1_MRuns great8.7 GB7.6
M3 Pro · 36 GBIQ3_MRuns great17 GB4.4
M3 Max · 36 GBIQ3_MRuns great17 GB8.3
M3 Max · 48 GBQ5_K_SRuns great23 GB8.6
M3 Max · 64 GBQ6_K_LRuns great31 GB7
M3 Max · 96 GBQ8_0Runs great40 GB5.4
M3 Max · 128 GBQ8_0Runs great47 GB7
M3 Ultra · 96 GBQ8_0Runs great40 GB13
M3 Ultra · 256 GBQ8_0Runs great47 GB13
M3 Ultra · 512 GBQ8_0Runs great47 GB13
M2 · 8 GBIQ1_SToo big21 GB
M2 · 16 GBIQ2_XSRuns well11 GB4.5
M2 · 24 GBQ3_K_MRuns well16 GB3.2
M2 Pro · 16 GBIQ2_XSRuns well11 GB8.5
M2 Pro · 32 GBQ4_1Runs well21 GB5.6
M2 Max · 32 GBQ4_1Runs well21 GB11
M2 Max · 64 GBQ6_K_LRuns great31 GB7
M2 Max · 96 GBQ8_0Runs great40 GB7
M2 Ultra · 64 GBQ6_K_LRuns great31 GB13
M2 Ultra · 128 GBQ8_0Runs great47 GB13
M2 Ultra · 192 GBQ8_0Runs great47 GB13
M1 · 8 GBIQ1_SToo big21 GB
M1 · 16 GBIQ2_XSRuns well11 GB3
M1 Pro · 16 GBIQ2_XSRuns well11 GB8
M1 Pro · 32 GBQ4_1Runs well21 GB5.4
M1 Max · 32 GBQ4_1Runs well21 GB9.8
M1 Max · 64 GBQ6_K_LRuns great31 GB6.6
M1 Ultra · 64 GBQ6_K_LRuns great31 GB12
M1 Ultra · 128 GBQ8_0Runs great47 GB12

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
TheDrummer
Released
September 2026
Parameters
31B
Longest chat
256K tokens
Reads pictures
Yes
Licence
Not stated
Downloads this month
92,362
Likes
45
Sizes
25, 9.2 to 61 GB
Kind
Maker's release

Badge for the model card

Shows on Artemis 31B V1.2'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