Outmake Models
Models

Swift 1.5 Ornith 9B

ukisai · October 2026

Get Hugging Face

A 9.2B chat model from ukisai that reads pictures as well as text.

Downloads
5.9K
Likes
24
Parameters
9.2B
Context
256K
Licence
apache-2.0

Runs great on M4 · 16 GB

The Q5_K_M size from ukisai is the one to get: a 6.6 GB download that uses 7.4 GB of memory, and writes about 8.6 words a second.

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

SizeDownloadMemory at 8KGet
Q4_K_M5.8 GB6.1 GBestimatedOpen
Q5_K_M6.6 GB6.9 GBestimatedOpen
Q6_K7.6 GB7.8 GBestimatedOpen
Q8_09.8 GB10 GBestimatedOpen
BF1618 GB19 GBestimatedOpen

Run It Anywhere

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

  • LM StudioMac, Windows, LinuxOpen
  • JanMac, Windows, LinuxOpen
  • MstyMac, Windows, LinuxOpen
  • OllamaMac, Windows, Linuxollama run hf.co/ukisai/Swift-1.5-Ornith-9B-GGUF:Q5_K_M
  • llama.cppMac, Windows, Linuxllama-server -hf ukisai/Swift-1.5-Ornith-9B-GGUF:Q5_K_M
  • Docker Model RunnerMac, Windows, Linuxdocker model run hf.co/ukisai/Swift-1.5-Ornith-9B-GGUF:Q5_K_M
On a PC Graphics Card
Video memoryLargest size that fitsDownloadMemory at 8K
6 GBNone worth runningneeds 6.1 GB
8 GBQ6_K7.6 GB7.8 GB
10 GBQ6_K7.6 GB7.8 GB
11 GBQ8_09.8 GB10 GB
12 GBQ8_09.8 GB10 GB
16 GBQ8_09.8 GB10 GB
20 GBBF1618 GB19 GB
24 GBBF1618 GB19 GB
32 GBBF1618 GB19 GB
48 GBBF1618 GB19 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 great7.4 GB12
M6 · 24 GBQ8_0Runs great11 GB10
M6 · 32 GBQ8_0Runs great15 GB10
M5 · 16 GBQ5_K_MRuns great7.4 GB11
M5 · 24 GBQ8_0Runs great11 GB9.4
M5 · 32 GBQ8_0Runs great15 GB9.4
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 GB27
M5 Max · 48 GBQ8_0Runs great15 GB36
M5 Max · 64 GBQ8_0Runs great15 GB36
M5 Max · 128 GBQ8_0Runs great15 GB36
M5 Ultra · 96 GBQ8_0Runs great15 GB68
M5 Ultra · 256 GBQ8_0Runs great15 GB68
M5 Ultra · 512 GBQ8_0Runs great15 GB68
M4 · 16 GBQ5_K_MRuns great7.4 GB8.6
M4 · 24 GBQ8_0Runs great11 GB7.1
M4 · 32 GBQ8_0Runs great15 GB7.1
M4 Pro · 24 GBQ8_0Runs great11 GB15
M4 Pro · 48 GBQ8_0Runs great15 GB15
M4 Pro · 64 GBQ8_0Runs great15 GB15
M4 Max · 36 GBQ8_0Runs great15 GB22
M4 Max · 48 GBQ8_0Runs great15 GB27
M4 Max · 64 GBQ8_0Runs great15 GB27
M4 Max · 96 GBQ8_0Runs great15 GB22
M4 Max · 128 GBQ8_0Runs great15 GB27
M3 · 8 GBQ3_K_LRuns well5.3 GB9.1
M3 · 16 GBQ5_K_MRuns great7.4 GB7.3
M3 · 24 GBQ8_0Runs great11 GB6
M3 Pro · 18 GBQ6_KRuns great8.3 GB9.6
M3 Pro · 36 GBQ8_0Runs great15 GB8.8
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 GB39
M3 Ultra · 256 GBQ8_0Runs great15 GB39
M3 Ultra · 512 GBQ8_0Runs great15 GB39
M2 · 8 GBQ3_K_LRuns well5.3 GB9
M2 · 16 GBQ5_K_MRuns great7.4 GB7.3
M2 · 24 GBQ8_0Runs great11 GB6
M2 Pro · 16 GBQ5_K_MRuns great7.4 GB14
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 GB38
M2 Ultra · 128 GBQ8_0Runs great15 GB38
M2 Ultra · 192 GBQ8_0Runs great15 GB38
M1 · 8 GBQ3_K_LRuns well5.3 GB6.1
M1 · 16 GBQ5_K_MRuns great7.4 GB4.9
M1 Pro · 16 GBQ5_K_MRuns great7.4 GB13
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 GB33
M1 Ultra · 128 GBQ8_0Runs great15 GB33

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

Packaged by

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

Information

Maker
ukisai
Released
October 2026
Parameters
9.2B
Longest chat
256K tokens
Reads pictures
Yes
Licence
apache-2.0
Downloads this month
5,915
Likes
24
Sizes
5, 5.8 to 18 GB
Kind
Maker's release

Badge for the model card

Shows on Swift 1.5 Ornith 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