Outmake Models
Models

POCKET Darwin 180B

FINAL-Bench · October 2026

Get Hugging Face

A 177B, 59B active chat model from FINAL-Bench.

Downloads
403K
Likes
69
Parameters
177B, 59B active
Context
256K
Licence
other

Too big for this Mac

Its smallest size needs 112 GB of memory, more than M4 · 16 GB can give it.

POCKET Darwin 180B 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 FINAL-Bench/POCKET-Darwin-180B-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.

SizeDownloadMemory at 8KGet
UD-Q4_K_XL111 GB111 GBestimatedOpen

Run It Anywhere

POCKET Darwin 180B is an open model, so any app that runs GGUF files can run it. These take the UD-Q4_K_XL size from FINAL-Bench straight from Hugging Face.

  • LM StudioMac, Windows, LinuxOpen
  • JanMac, Windows, LinuxOpen
  • MstyMac, Windows, LinuxOpen
  • OllamaMac, Windows, Linuxollama run hf.co/FINAL-Bench/POCKET-Darwin-180B-GGUF:UD-Q4_K_XL
  • llama.cppMac, Windows, Linuxllama-server -hf FINAL-Bench/POCKET-Darwin-180B-GGUF:UD-Q4_K_XL
  • Docker Model RunnerMac, Windows, Linuxdocker model run hf.co/FINAL-Bench/POCKET-Darwin-180B-GGUF:UD-Q4_K_XL
On a PC Graphics Card
Video memoryLargest size that fitsDownloadMemory at 8K
6 GBNone worth runningneeds 111 GB
8 GBNone worth runningneeds 111 GB
10 GBNone worth runningneeds 111 GB
11 GBNone worth runningneeds 111 GB
12 GBNone worth runningneeds 111 GB
16 GBNone worth runningneeds 111 GB
20 GBNone worth runningneeds 111 GB
24 GBNone worth runningneeds 111 GB
32 GBNone worth runningneeds 111 GB
48 GBNone worth runningneeds 111 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-Q4_K_XLToo big112 GB
M6 · 24 GBUD-Q4_K_XLToo big112 GB
M6 · 32 GBUD-Q4_K_XLToo big112 GB
M5 · 16 GBUD-Q4_K_XLToo big112 GB
M5 · 24 GBUD-Q4_K_XLToo big112 GB
M5 · 32 GBUD-Q4_K_XLToo big112 GB
M5 Pro · 24 GBUD-Q4_K_XLToo big112 GB
M5 Pro · 48 GBUD-Q4_K_XLToo big112 GB
M5 Pro · 64 GBUD-Q4_K_XLToo big112 GB
M5 Max · 36 GBUD-Q4_K_XLToo big112 GB
M5 Max · 48 GBUD-Q4_K_XLToo big112 GB
M5 Max · 64 GBUD-Q4_K_XLToo big112 GB
M5 Max · 128 GBUD-Q4_K_XLToo big112 GB
M5 Ultra · 96 GBUD-Q4_K_XLToo big112 GB
M5 Ultra · 256 GBUD-Q4_K_XLRuns great112 GB12
M5 Ultra · 512 GBUD-Q4_K_XLRuns great112 GB12
M4 · 16 GBUD-Q4_K_XLToo big112 GB
M4 · 24 GBUD-Q4_K_XLToo big112 GB
M4 · 32 GBUD-Q4_K_XLToo big112 GB
M4 Pro · 24 GBUD-Q4_K_XLToo big112 GB
M4 Pro · 48 GBUD-Q4_K_XLToo big112 GB
M4 Pro · 64 GBUD-Q4_K_XLToo big112 GB
M4 Max · 36 GBUD-Q4_K_XLToo big112 GB
M4 Max · 48 GBUD-Q4_K_XLToo big112 GB
M4 Max · 64 GBUD-Q4_K_XLToo big112 GB
M4 Max · 96 GBUD-Q4_K_XLToo big112 GB
M4 Max · 128 GBUD-Q4_K_XLToo big112 GB
M3 · 8 GBUD-Q4_K_XLToo big112 GB
M3 · 16 GBUD-Q4_K_XLToo big112 GB
M3 · 24 GBUD-Q4_K_XLToo big112 GB
M3 Pro · 18 GBUD-Q4_K_XLToo big112 GB
M3 Pro · 36 GBUD-Q4_K_XLToo big112 GB
M3 Max · 36 GBUD-Q4_K_XLToo big112 GB
M3 Max · 48 GBUD-Q4_K_XLToo big112 GB
M3 Max · 64 GBUD-Q4_K_XLToo big112 GB
M3 Max · 96 GBUD-Q4_K_XLToo big112 GB
M3 Max · 128 GBUD-Q4_K_XLToo big112 GB
M3 Ultra · 96 GBUD-Q4_K_XLToo big112 GB
M3 Ultra · 256 GBUD-Q4_K_XLRuns great112 GB8
M3 Ultra · 512 GBUD-Q4_K_XLRuns great112 GB8
M2 · 8 GBUD-Q4_K_XLToo big112 GB
M2 · 16 GBUD-Q4_K_XLToo big112 GB
M2 · 24 GBUD-Q4_K_XLToo big112 GB
M2 Pro · 16 GBUD-Q4_K_XLToo big112 GB
M2 Pro · 32 GBUD-Q4_K_XLToo big112 GB
M2 Max · 32 GBUD-Q4_K_XLToo big112 GB
M2 Max · 64 GBUD-Q4_K_XLToo big112 GB
M2 Max · 96 GBUD-Q4_K_XLToo big112 GB
M2 Ultra · 64 GBUD-Q4_K_XLToo big112 GB
M2 Ultra · 128 GBUD-Q4_K_XLToo big112 GB
M2 Ultra · 192 GBUD-Q4_K_XLRuns great112 GB8
M1 · 8 GBUD-Q4_K_XLToo big112 GB
M1 · 16 GBUD-Q4_K_XLToo big112 GB
M1 Pro · 16 GBUD-Q4_K_XLToo big112 GB
M1 Pro · 32 GBUD-Q4_K_XLToo big112 GB
M1 Max · 32 GBUD-Q4_K_XLToo big112 GB
M1 Max · 64 GBUD-Q4_K_XLToo big112 GB
M1 Ultra · 64 GBUD-Q4_K_XLToo big112 GB
M1 Ultra · 128 GBUD-Q4_K_XLToo big112 GB

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

Information

Maker
FINAL-Bench
Released
October 2026
Parameters
177B, 59B active
Longest chat
256K tokens
Reads pictures
No
Licence
other
Downloads this month
403,459
Likes
69
Sizes
1, 111 to 111 GB
Kind
Maker's release

Badge for the model card

Shows on POCKET Darwin 180B'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