Outmake Models
Models

Diplodocus Preview

OsaurusAI · October 2026

Get Hugging Face

A 9B chat model from OsaurusAI.

Downloads
447K
Likes
1
Parameters
9B
Context
512K
Licence
apache-2.0

Runs great on M4 · 16 GB

The Q4_K_M size from OsaurusAI is the one to get: a 6.3 GB download that uses 7.1 GB of memory, and writes about 6.2 words a second.

Diplodocus Preview runs well from a Mac with an M1 and 16 GB of memory. 56 of 59 Mac configurations run it well.

Compare with

The nearest models in size.

Sizes

From OsaurusAI/Diplodocus-preview-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.

SizeDownloadMemory at 8KGet
Q4_K_M6.3 GB7.1 GBestimatedOpen
Q6_K7.8 GB8.6 GBestimatedOpen
Q8_09.6 GB10 GBestimatedOpen

Run It Anywhere

Diplodocus Preview is an open model, so any app that runs GGUF files can run it. These take the Q4_K_M size from OsaurusAI straight from Hugging Face.

  • LM StudioMac, Windows, LinuxOpen
  • JanMac, Windows, LinuxOpen
  • MstyMac, Windows, LinuxOpen
  • OllamaMac, Windows, Linuxollama run hf.co/OsaurusAI/Diplodocus-preview-GGUF:Q4_K_M
  • llama.cppMac, Windows, Linuxllama-server -hf OsaurusAI/Diplodocus-preview-GGUF:Q4_K_M
  • Docker Model RunnerMac, Windows, Linuxdocker model run hf.co/OsaurusAI/Diplodocus-preview-GGUF:Q4_K_M
On a PC Graphics Card
Video memoryLargest size that fitsDownloadMemory at 8K
6 GBNone worth runningneeds 7.1 GB
8 GBQ4_K_M6.3 GB7.1 GB
10 GBQ6_K7.8 GB8.6 GB
11 GBQ8_09.6 GB10 GB
12 GBQ8_09.6 GB10 GB
16 GBQ8_09.6 GB10 GB
20 GBQ8_09.6 GB10 GB
24 GBQ8_09.6 GB10 GB
32 GBQ8_09.6 GB10 GB
48 GBQ8_09.6 GB10 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 GBQ4_K_MRuns great7.1 GB8.7
M6 · 24 GBQ8_0Runs great11 GB8
M6 · 32 GBQ8_0Runs great15 GB8
M5 · 16 GBQ4_K_MRuns great7.1 GB7.9
M5 · 24 GBQ8_0Runs great11 GB7.2
M5 · 32 GBQ8_0Runs great15 GB7.2
M5 Pro · 24 GBQ8_0Runs great11 GB14
M5 Pro · 48 GBQ8_0Runs great21 GB14
M5 Pro · 64 GBQ8_0Runs great21 GB14
M5 Max · 36 GBQ8_0Runs great15 GB21
M5 Max · 48 GBQ8_0Runs great21 GB28
M5 Max · 64 GBQ8_0Runs great21 GB28
M5 Max · 128 GBQ8_0Runs great53 GB28
M5 Ultra · 96 GBQ8_0Runs great32 GB53
M5 Ultra · 256 GBQ8_0Runs great53 GB53
M5 Ultra · 512 GBQ8_0Runs great53 GB53
M4 · 16 GBQ4_K_MRuns great7.1 GB6.2
M4 · 24 GBQ8_0Runs great11 GB5.5
M4 · 32 GBQ8_0Runs great15 GB5.5
M4 Pro · 24 GBQ8_0Runs great11 GB12
M4 Pro · 48 GBQ8_0Runs great21 GB12
M4 Pro · 64 GBQ8_0Runs great21 GB12
M4 Max · 36 GBQ8_0Runs great15 GB17
M4 Max · 48 GBQ8_0Runs great21 GB22
M4 Max · 64 GBQ8_0Runs great21 GB22
M4 Max · 96 GBQ8_0Runs great32 GB17
M4 Max · 128 GBQ8_0Runs great53 GB22
M3 · 8 GBQ4_K_MToo big50 GB
M3 · 16 GBQ4_K_MRuns great7.1 GB5.2
M3 · 24 GBQ8_0Runs great11 GB4.6
M3 Pro · 18 GBQ6_KRuns great8.6 GB6.9
M3 Pro · 36 GBQ8_0Runs great15 GB6.8
M3 Max · 36 GBQ8_0Runs great15 GB13
M3 Max · 48 GBQ8_0Runs great21 GB17
M3 Max · 64 GBQ8_0Runs great21 GB17
M3 Max · 96 GBQ8_0Runs great32 GB13
M3 Max · 128 GBQ8_0Runs great53 GB17
M3 Ultra · 96 GBQ8_0Runs great32 GB31
M3 Ultra · 256 GBQ8_0Runs great53 GB31
M3 Ultra · 512 GBQ8_0Runs great53 GB31
M2 · 8 GBQ4_K_MToo big50 GB
M2 · 16 GBQ4_K_MRuns great7.1 GB5.2
M2 · 24 GBQ8_0Runs great11 GB4.6
M2 Pro · 16 GBQ4_K_MRuns great7.1 GB10
M2 Pro · 32 GBQ8_0Runs great15 GB9
M2 Max · 32 GBQ8_0Runs great15 GB17
M2 Max · 64 GBQ8_0Runs great21 GB17
M2 Max · 96 GBQ8_0Runs great32 GB17
M2 Ultra · 64 GBQ8_0Runs great21 GB31
M2 Ultra · 128 GBQ8_0Runs great53 GB31
M2 Ultra · 192 GBQ8_0Runs great53 GB31
M1 · 8 GBQ4_K_MToo big50 GB
M1 · 16 GBQ4_K_MRuns great7.1 GB3.5
M1 Pro · 16 GBQ4_K_MRuns great7.1 GB9.6
M1 Pro · 32 GBQ8_0Runs great15 GB8.6
M1 Max · 32 GBQ8_0Runs great15 GB16
M1 Max · 64 GBQ8_0Runs great21 GB16
M1 Ultra · 64 GBQ8_0Runs great21 GB27
M1 Ultra · 128 GBQ8_0Runs great53 GB27

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

Information

Maker
OsaurusAI
Released
October 2026
Parameters
9B
Longest chat
512K tokens
Reads pictures
No
Licence
apache-2.0
Downloads this month
446,846
Likes
1
Sizes
3, 6.3 to 9.6 GB
Kind
Maker's release

Badge for the model card

Shows on Diplodocus Preview'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