Outmake Models
Models

Ornith 1.0 397B

ornith-ai · July 2026

Get Hugging Face

A 396B, 17B active chat model from ornith-ai.

Downloads
3.5K
Likes
23
Parameters
396B, 17B active
Context
256K
Licence
mit

Too big for this Mac

Its smallest size needs 117 GB of memory, more than M4 · 16 GB can give it.

Ratings

Software fixesSWE-bench Verified
82.4%

SWE-bench Verified: real GitHub issues fixed so the project's tests pass. Scores are the ones filed on the model's Hugging Face page or the board's own table, read 2026-11-05; some come from the maker.

Ornith 1.0 397B runs well from a Mac with an M2 Ultra and 192 GB of memory. 5 of 59 Mac configurations run it well.

Compare with

The nearest models in size.

Sizes

From unsloth/Ornith-1.0-397B-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.

SizeDownloadMemory at 8KGet
UD-IQ1_S113 GB113 GBestimatedOpen
UD-IQ1_M119 GB119 GBestimatedOpen
UD-IQ2_XXS124 GB124 GBestimatedOpen
UD-IQ2_M124 GB125 GBestimatedOpen
UD-Q2_K_XL133 GB133 GBestimatedOpen
UD-IQ3_XXS148 GB148 GBestimatedOpen
UD-IQ3_S162 GB162 GBestimatedOpen
UD-Q3_K_M180 GB180 GBestimatedOpen
UD-Q3_K_XL180 GB180 GBestimatedOpen
UD-IQ4_XS192 GB192 GBestimatedOpen
UD-IQ4_NL196 GB196 GBestimatedOpen
UD-Q4_K_S230 GB230 GBestimatedOpen
MXFP4_MOE238 GB238 GBestimatedOpen
UD-Q4_K_M245 GB245 GBestimatedOpen
UD-Q4_K_XL246 GB246 GBestimatedOpen
UD-Q5_K_S277 GB278 GBestimatedOpen
UD-Q5_K_M295 GB296 GBestimatedOpen
UD-Q5_K_XL296 GB296 GBestimatedOpen
UD-Q6_K330 GB330 GBestimatedOpen
UD-Q6_K_XL360 GB360 GBestimatedOpen
Q8_0422 GB422 GBestimatedOpen
UD-Q8_K_XL432 GB432 GBestimatedOpen
BF16793 GB793 GBestimatedOpen

Run It Anywhere

Ornith 1.0 397B is an open model, so any app that runs GGUF files can run it. These take the UD-IQ1_S size from unsloth straight from Hugging Face.

  • LM StudioMac, Windows, LinuxOpen
  • JanMac, Windows, LinuxOpen
  • MstyMac, Windows, LinuxOpen
  • OllamaMac, Windows, Linuxollama run hf.co/unsloth/Ornith-1.0-397B-GGUF:UD-IQ1_S
  • llama.cppMac, Windows, Linuxllama-server -hf unsloth/Ornith-1.0-397B-GGUF:UD-IQ1_S
  • Docker Model RunnerMac, Windows, Linuxdocker model run hf.co/unsloth/Ornith-1.0-397B-GGUF:UD-IQ1_S
On a PC Graphics Card
Video memoryLargest size that fitsDownloadMemory at 8K
6 GBNone worth runningneeds 125 GB
8 GBNone worth runningneeds 125 GB
10 GBNone worth runningneeds 125 GB
11 GBNone worth runningneeds 125 GB
12 GBNone worth runningneeds 125 GB
16 GBNone worth runningneeds 125 GB
20 GBNone worth runningneeds 125 GB
24 GBNone worth runningneeds 125 GB
32 GBNone worth runningneeds 125 GB
48 GBNone worth runningneeds 125 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-IQ1_SToo big117 GB
M6 · 24 GBUD-IQ1_SToo big117 GB
M6 · 32 GBUD-IQ1_SToo big117 GB
M5 · 16 GBUD-IQ1_SToo big117 GB
M5 · 24 GBUD-IQ1_SToo big117 GB
M5 · 32 GBUD-IQ1_SToo big117 GB
M5 Pro · 24 GBUD-IQ1_SToo big117 GB
M5 Pro · 48 GBUD-IQ1_SToo big117 GB
M5 Pro · 64 GBUD-IQ1_SToo big117 GB
M5 Max · 36 GBUD-IQ1_SToo big117 GB
M5 Max · 48 GBUD-IQ1_SToo big117 GB
M5 Max · 64 GBUD-IQ1_SToo big117 GB
M5 Max · 128 GBUD-IQ1_SToo big117 GB
M5 Ultra · 96 GBUD-IQ1_SToo big117 GB
M5 Ultra · 256 GBUD-IQ4_NLRuns well201 GB40
M5 Ultra · 512 GBUD-Q6_KRuns great334 GB27
M4 · 16 GBUD-IQ1_SToo big117 GB
M4 · 24 GBUD-IQ1_SToo big117 GB
M4 · 32 GBUD-IQ1_SToo big117 GB
M4 Pro · 24 GBUD-IQ1_SToo big117 GB
M4 Pro · 48 GBUD-IQ1_SToo big117 GB
M4 Pro · 64 GBUD-IQ1_SToo big117 GB
M4 Max · 36 GBUD-IQ1_SToo big117 GB
M4 Max · 48 GBUD-IQ1_SToo big117 GB
M4 Max · 64 GBUD-IQ1_SToo big117 GB
M4 Max · 96 GBUD-IQ1_SToo big117 GB
M4 Max · 128 GBUD-IQ1_SToo big117 GB
M3 · 8 GBUD-IQ1_SToo big117 GB
M3 · 16 GBUD-IQ1_SToo big117 GB
M3 · 24 GBUD-IQ1_SToo big117 GB
M3 Pro · 18 GBUD-IQ1_SToo big117 GB
M3 Pro · 36 GBUD-IQ1_SToo big117 GB
M3 Max · 36 GBUD-IQ1_SToo big117 GB
M3 Max · 48 GBUD-IQ1_SToo big117 GB
M3 Max · 64 GBUD-IQ1_SToo big117 GB
M3 Max · 96 GBUD-IQ1_SToo big117 GB
M3 Max · 128 GBUD-IQ1_SToo big117 GB
M3 Ultra · 96 GBUD-IQ1_SToo big117 GB
M3 Ultra · 256 GBUD-IQ4_NLRuns well201 GB22
M3 Ultra · 512 GBUD-Q6_KRuns great334 GB16
M2 · 8 GBUD-IQ1_SToo big117 GB
M2 · 16 GBUD-IQ1_SToo big117 GB
M2 · 24 GBUD-IQ1_SToo big117 GB
M2 Pro · 16 GBUD-IQ1_SToo big117 GB
M2 Pro · 32 GBUD-IQ1_SToo big117 GB
M2 Max · 32 GBUD-IQ1_SToo big117 GB
M2 Max · 64 GBUD-IQ1_SToo big117 GB
M2 Max · 96 GBUD-IQ1_SToo big117 GB
M2 Ultra · 64 GBUD-IQ1_SToo big117 GB
M2 Ultra · 128 GBUD-IQ1_SToo big117 GB
M2 Ultra · 192 GBUD-IQ3_XXSRuns well152 GB25
M1 · 8 GBUD-IQ1_SToo big117 GB
M1 · 16 GBUD-IQ1_SToo big117 GB
M1 Pro · 16 GBUD-IQ1_SToo big117 GB
M1 Pro · 32 GBUD-IQ1_SToo big117 GB
M1 Max · 32 GBUD-IQ1_SToo big117 GB
M1 Max · 64 GBUD-IQ1_SToo big117 GB
M1 Ultra · 64 GBUD-IQ1_SToo big117 GB
M1 Ultra · 128 GBUD-IQ1_SToo big117 GB

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

Information

Maker
ornith-ai
Released
July 2026
Parameters
396B, 17B active
Longest chat
256K tokens
Reads pictures
No
Licence
mit
Downloads this month
3,498
Likes
23
Sizes
23, 113 to 793 GB
Kind
Maker's release

Badge for the model card

Shows on Ornith 1.0 397B'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