Outmake Models
Models

Ornith 1.0 9B

ornith-ai · June 2026

Get Hugging Face

A 8.9B chat model from ornith-ai that reads pictures as well as text.

Downloads
2.8M
Likes
858
Parameters
8.9B
Context
256K
Licence
mit

Runs great on M4 · 16 GB

The Q6_K size from ornith-ai is the one to get: a 7.4 GB download that uses 7.6 GB of memory, and writes about 7.9 words a second.

Ornith 1.0 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 unsloth/Ornith-1.0-9B-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.

SizeDownloadMemory at 8KGet
UD-IQ2_M3.9 GB4.1 GBestimatedOpen
UD-IQ3_XXS4.2 GB4.4 GBestimatedOpen
UD-Q2_K_XL4.3 GB4.6 GBestimatedOpen
Q3_K_S4.3 GB4.6 GBestimatedOpen
Q3_K_M4.7 GB5.0 GBestimatedOpen
UD-Q3_K_XL5.1 GB5.4 GBestimatedOpen
IQ4_XS5.3 GB5.6 GBestimatedOpen
Q4_05.4 GB5.7 GBestimatedOpen
Q4_K_S5.4 GB5.7 GBestimatedOpen
IQ4_NL5.5 GB5.8 GBestimatedOpen
Q4_15.9 GB6.1 GBestimatedOpen
UD-Q4_K_XL6.0 GB6.3 GBestimatedOpen
Q5_K_S6.4 GB6.7 GBestimatedOpen
UD-Q5_K_XL6.7 GB7.0 GBestimatedOpen
UD-Q6_K_XL8.8 GB9.0 GBestimatedOpen
UD-Q8_K_XL13 GB13 GBestimatedOpen

Run It Anywhere

Ornith 1.0 9B is an open model, so any app that runs GGUF files can run it. These take the Q6_K size from ornith-ai straight from Hugging Face.

  • LM StudioMac, Windows, LinuxOpen
  • JanMac, Windows, LinuxOpen
  • MstyMac, Windows, LinuxOpen
  • OllamaMac, Windows, Linuxollama run hf.co/ornith-ai/Ornith-1.0-9B-GGUF:Q6_K
  • llama.cppMac, Windows, Linuxllama-server -hf ornith-ai/Ornith-1.0-9B-GGUF:Q6_K
  • Docker Model RunnerMac, Windows, Linuxdocker model run hf.co/ornith-ai/Ornith-1.0-9B-GGUF:Q6_K
On a PC Graphics Card
Video memoryLargest size that fitsDownloadMemory at 8K
6 GBIQ4_NL5.5 GB5.8 GB
8 GBUD-Q5_K_XL6.7 GB7.0 GB
10 GBUD-Q6_K_XL8.8 GB9.0 GB
11 GBUD-Q6_K_XL8.8 GB9.0 GB
12 GBUD-Q6_K_XL8.8 GB9.0 GB
16 GBUD-Q8_K_XL13 GB13 GB
20 GBUD-Q8_K_XL13 GB13 GB
24 GBUD-Q8_K_XL13 GB13 GB
32 GBUD-Q8_K_XL13 GB13 GB
48 GBUD-Q8_K_XL13 GB13 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 GBQ6_KRuns great7.6 GB12
M6 · 24 GBQ8_0Runs great11 GB11
M6 · 32 GBQ8_0Runs great15 GB11
M5 · 16 GBQ6_KRuns great7.6 GB11
M5 · 24 GBQ8_0Runs great11 GB9.6
M5 · 32 GBQ8_0Runs great15 GB9.6
M5 Pro · 24 GBQ8_0Runs great11 GB19
M5 Pro · 48 GBQ8_0Runs great15 GB19
M5 Pro · 64 GBQ8_0Runs great15 GB19
M5 Max · 36 GBQ8_0Runs great15 GB28
M5 Max · 48 GBQ8_0Runs great15 GB37
M5 Max · 64 GBQ8_0Runs great15 GB37
M5 Max · 128 GBQ8_0Runs great15 GB37
M5 Ultra · 96 GBQ8_0Runs great15 GB69
M5 Ultra · 256 GBQ8_0Runs great15 GB69
M5 Ultra · 512 GBQ8_0Runs great15 GB69
M4 · 16 GBQ6_KRuns great7.6 GB7.9
M4 · 24 GBQ8_0Runs great11 GB7.3
M4 · 32 GBQ8_0Runs great15 GB7.3
M4 Pro · 24 GBQ8_0Runs great11 GB16
M4 Pro · 48 GBQ8_0Runs great15 GB16
M4 Pro · 64 GBQ8_0Runs great15 GB16
M4 Max · 36 GBQ8_0Runs great15 GB22
M4 Max · 48 GBQ8_0Runs great15 GB28
M4 Max · 64 GBQ8_0Runs great15 GB28
M4 Max · 96 GBQ8_0Runs great15 GB22
M4 Max · 128 GBQ8_0Runs great15 GB28
M3 · 8 GBQ3_K_MRuns well5.1 GB9.6
M3 · 16 GBQ6_KRuns great7.6 GB6.7
M3 · 24 GBQ8_0Runs great11 GB6.1
M3 Pro · 18 GBQ6_KRuns great8.1 GB9.9
M3 Pro · 36 GBQ8_0Runs great15 GB9.1
M3 Max · 36 GBQ8_0Runs great15 GB17
M3 Max · 48 GBQ8_0Runs great15 GB22
M3 Max · 64 GBQ8_0Runs great15 GB22
M3 Max · 96 GBQ8_0Runs great15 GB17
M3 Max · 128 GBQ8_0Runs great15 GB22
M3 Ultra · 96 GBQ8_0Runs great15 GB40
M3 Ultra · 256 GBQ8_0Runs great15 GB40
M3 Ultra · 512 GBQ8_0Runs great15 GB40
M2 · 8 GBQ3_K_MRuns well5.1 GB9.6
M2 · 16 GBQ6_KRuns great7.6 GB6.7
M2 · 24 GBQ8_0Runs great11 GB6.1
M2 Pro · 16 GBQ6_KRuns great7.6 GB13
M2 Pro · 32 GBQ8_0Runs great15 GB12
M2 Max · 32 GBQ8_0Runs great15 GB22
M2 Max · 64 GBQ8_0Runs great15 GB22
M2 Max · 96 GBQ8_0Runs great15 GB22
M2 Ultra · 64 GBQ8_0Runs great15 GB39
M2 Ultra · 128 GBQ8_0Runs great15 GB39
M2 Ultra · 192 GBQ8_0Runs great15 GB39
M1 · 8 GBQ3_K_MRuns well5.1 GB6.5
M1 · 16 GBQ6_KRuns great7.6 GB4.5
M1 Pro · 16 GBQ6_KRuns great7.6 GB12
M1 Pro · 32 GBQ8_0Runs great15 GB11
M1 Max · 32 GBQ8_0Runs great15 GB20
M1 Max · 64 GBQ8_0Runs great15 GB20
M1 Ultra · 64 GBQ8_0Runs great15 GB34
M1 Ultra · 128 GBQ8_0Runs great15 GB34

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
ornith-ai
Released
June 2026
Parameters
8.9B
Longest chat
256K tokens
Reads pictures
Yes
Licence
mit
Downloads this month
2,795,688
Likes
858
Sizes
16, 3.9 to 13 GB
Kind
Maker's release

Badge for the model card

Shows on Ornith 1.0 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