Outmake Models
Models

Ornith 1.5 9B

ornith-ai · August 2026

Get Hugging Face

A 9.2B chat model from ornith-ai that reads pictures as well as text.

Downloads
5.6M
Likes
796
Parameters
9.2B
Context
256K
Licence
mit

Runs great on M4 · 16 GB

The Q5_K_M size from Mungert is the one to get: a 6.9 GB download that uses 7.7 GB of memory, and writes about 8.3 words a second.

Ornith 1.5 9B 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/Ornith-1.5-9B-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.

SizeDownloadMemory at 8KGet
IQ2_M3.8 GB4.0 GBestimatedOpen
Q2_K4.1 GB4.3 GBestimatedOpen
IQ3_XXS4.3 GB4.5 GBestimatedOpen
IQ3_XS4.6 GB4.8 GBestimatedOpen
Q3_K_S4.7 GB4.9 GBestimatedOpen
IQ3_M4.7 GB5.0 GBestimatedOpen
Q3_K_M4.9 GB5.2 GBestimatedOpen
Q2_K_L5.1 GB5.3 GBestimatedOpen
Q3_K_L5.1 GB5.4 GBestimatedOpen
IQ4_XS5.2 GB5.5 GBestimatedOpen
IQ4_NL5.5 GB5.8 GBestimatedOpen
Q4_05.5 GB5.8 GBestimatedOpen
Q4_K_S5.6 GB5.9 GBestimatedOpen
Q4_15.9 GB6.2 GBestimatedOpen
Q3_K_XL6.0 GB6.3 GBestimatedOpen
Q5_K_S6.5 GB6.8 GBestimatedOpen
Q4_K_L6.7 GB6.9 GBestimatedOpen

Run It Anywhere

Ornith 1.5 9B is an open model, so any app that runs GGUF files can run it. These take the Q5_K_M size from Mungert straight from Hugging Face.

  • LM StudioMac, Windows, LinuxOpen
  • JanMac, Windows, LinuxOpen
  • MstyMac, Windows, LinuxOpen
  • OllamaMac, Windows, Linuxollama run hf.co/Mungert/Ornith-1.5-9B-GGUF:Q5_K_M
  • llama.cppMac, Windows, Linuxllama-server -hf Mungert/Ornith-1.5-9B-GGUF:Q5_K_M
  • Docker Model RunnerMac, Windows, Linuxdocker model run hf.co/Mungert/Ornith-1.5-9B-GGUF:Q5_K_M
On a PC Graphics Card
Video memoryLargest size that fitsDownloadMemory at 8K
6 GBQ4_K_S5.6 GB5.9 GB
8 GBQ4_K_L6.7 GB6.9 GB
10 GBQ4_K_L6.7 GB6.9 GB
11 GBQ4_K_L6.7 GB6.9 GB
12 GBQ4_K_L6.7 GB6.9 GB
16 GBQ4_K_L6.7 GB6.9 GB
20 GBQ4_K_L6.7 GB6.9 GB
24 GBQ4_K_L6.7 GB6.9 GB
32 GBQ4_K_L6.7 GB6.9 GB
48 GBQ4_K_L6.7 GB6.9 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 GBQ5_K_MRuns great7.7 GB12
M6 · 24 GBQ5_K_MRuns great9.7 GB12
M6 · 32 GBQ5_K_MRuns great12 GB12
M5 · 16 GBQ5_K_MRuns great7.7 GB11
M5 · 24 GBQ5_K_MRuns great9.7 GB11
M5 · 32 GBQ5_K_MRuns great12 GB11
M5 Pro · 24 GBQ5_K_MRuns great9.7 GB21
M5 Pro · 48 GBQ5_K_MRuns great12 GB21
M5 Pro · 64 GBQ5_K_MRuns great12 GB21
M5 Max · 36 GBQ5_K_MRuns great12 GB31
M5 Max · 48 GBQ5_K_MRuns great12 GB40
M5 Max · 64 GBQ5_K_MRuns great12 GB40
M5 Max · 128 GBQ5_K_MRuns great12 GB40
M5 Ultra · 96 GBQ5_K_MRuns great12 GB74
M5 Ultra · 256 GBQ5_K_MRuns great12 GB74
M5 Ultra · 512 GBQ5_K_MRuns great12 GB74
M4 · 16 GBQ5_K_MRuns great7.7 GB8.3
M4 · 24 GBQ5_K_MRuns great9.7 GB8.3
M4 · 32 GBQ5_K_MRuns great12 GB8.3
M4 Pro · 24 GBQ5_K_MRuns great9.7 GB17
M4 Pro · 48 GBQ5_K_MRuns great12 GB17
M4 Pro · 64 GBQ5_K_MRuns great12 GB17
M4 Max · 36 GBQ5_K_MRuns great12 GB25
M4 Max · 48 GBQ5_K_MRuns great12 GB31
M4 Max · 64 GBQ5_K_MRuns great12 GB31
M4 Max · 96 GBQ5_K_MRuns great12 GB25
M4 Max · 128 GBQ5_K_MRuns great12 GB31
M3 · 8 GBQ3_K_SRuns well5.3 GB9.1
M3 · 16 GBQ5_K_MRuns great7.7 GB7
M3 · 24 GBQ5_K_MRuns great9.7 GB7
M3 Pro · 18 GBQ5_K_MRuns great8.4 GB10
M3 Pro · 36 GBQ5_K_MRuns great12 GB10
M3 Max · 36 GBQ5_K_MRuns great12 GB19
M3 Max · 48 GBQ5_K_MRuns great12 GB25
M3 Max · 64 GBQ5_K_MRuns great12 GB25
M3 Max · 96 GBQ5_K_MRuns great12 GB19
M3 Max · 128 GBQ5_K_MRuns great12 GB25
M3 Ultra · 96 GBQ5_K_MRuns great12 GB43
M3 Ultra · 256 GBQ5_K_MRuns great12 GB43
M3 Ultra · 512 GBQ5_K_MRuns great12 GB43
M2 · 8 GBQ3_K_SRuns well5.3 GB9.1
M2 · 16 GBQ5_K_MRuns great7.7 GB7
M2 · 24 GBQ5_K_MRuns great9.7 GB7
M2 Pro · 16 GBQ5_K_MRuns great7.7 GB13
M2 Pro · 32 GBQ5_K_MRuns great12 GB13
M2 Max · 32 GBQ5_K_MRuns great12 GB25
M2 Max · 64 GBQ5_K_MRuns great12 GB25
M2 Max · 96 GBQ5_K_MRuns great12 GB25
M2 Ultra · 64 GBQ5_K_MRuns great12 GB43
M2 Ultra · 128 GBQ5_K_MRuns great12 GB43
M2 Ultra · 192 GBQ5_K_MRuns great12 GB43
M1 · 8 GBQ3_K_SRuns well5.3 GB6.1
M1 · 16 GBQ5_K_MRuns great7.7 GB4.8
M1 Pro · 16 GBQ5_K_MRuns great7.7 GB13
M1 Pro · 32 GBQ5_K_MRuns great12 GB13
M1 Max · 32 GBQ5_K_MRuns great12 GB22
M1 Max · 64 GBQ5_K_MRuns great12 GB22
M1 Ultra · 64 GBQ5_K_MRuns great12 GB36
M1 Ultra · 128 GBQ5_K_MRuns great12 GB36

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

Packaged by

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

Information

Maker
ornith-ai
Released
August 2026
Parameters
9.2B
Longest chat
256K tokens
Reads pictures
Yes
Licence
mit
Downloads this month
5,598,695
Likes
796
Sizes
17, 3.8 to 6.7 GB
Kind
Maker's release

Badge for the model card

Shows on Ornith 1.5 9B'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