Outmake Models
Models

DeepSeek R1

DeepSeek · January 2025

Get Hugging Face

A community version of another maker's model.

Rating
4.0
Downloads
41K
Likes
1.1K
Parameters
671B, 38B active
Context
160K
Licence
mit

Too big for this Mac

Its smallest size needs 145 GB of memory, more than M4 · 16 GB can give it.

Ratings

4.0 out of 5, across people's blind votes on its answers.

Text
1398
Coding
1444

LM Arena ratings of October 28, 2026 (CC BY 4.0): people vote between two answers without knowing which model wrote which. The bar ends at 1488, the best any open model has. The Arena tests the full model; a small size on a Mac answers a little worse.

DeepSeek R1 runs well from a Mac with an M2 Ultra and 192 GB of memory. 5 of 59 Mac configurations run it well. It is a re-tune or merge made by someone other than the original model's maker, so its ratings, where it has any, are its own.

Compare with

The nearest models in size.

Sizes

From unsloth/DeepSeek-R1-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.

SizeDownloadMemory at 8KGet
UD-IQ1_S140 GB141 GBestimatedOpen
UD-IQ1_M169 GB169 GBestimatedOpen
UD-IQ2_XXS196 GB197 GBestimatedOpen
Q2_K_XS221 GB222 GBestimatedOpen
UD-Q2_K_XL227 GB227 GBestimatedOpen
Q2_K244 GB244 GBestimatedOpen
Q2_K_L244 GB245 GBestimatedOpen
Q3_K_M319 GB320 GBestimatedOpen
Q4_K_M404 GB405 GBestimatedOpen
Q5_K_M475 GB476 GBestimatedOpen
Q6_K551 GB551 GBestimatedOpen
Q8_0713 GB714 GBestimatedOpen
BF161342 GB1343 GBestimatedOpen

Run It Anywhere

DeepSeek R1 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/DeepSeek-R1-GGUF:UD-IQ1_S
  • llama.cppMac, Windows, Linuxllama-server -hf unsloth/DeepSeek-R1-GGUF:UD-IQ1_S
  • Docker Model RunnerMac, Windows, Linuxdocker model run hf.co/unsloth/DeepSeek-R1-GGUF:UD-IQ1_S
On a PC Graphics Card
Video memoryLargest size that fitsDownloadMemory at 8K
6 GBNone worth runningneeds 227 GB
8 GBNone worth runningneeds 227 GB
10 GBNone worth runningneeds 227 GB
11 GBNone worth runningneeds 227 GB
12 GBNone worth runningneeds 227 GB
16 GBNone worth runningneeds 227 GB
20 GBNone worth runningneeds 227 GB
24 GBNone worth runningneeds 227 GB
32 GBNone worth runningneeds 227 GB
48 GBNone worth runningneeds 227 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 big145 GB
M6 · 24 GBUD-IQ1_SToo big145 GB
M6 · 32 GBUD-IQ1_SToo big145 GB
M5 · 16 GBUD-IQ1_SToo big145 GB
M5 · 24 GBUD-IQ1_SToo big145 GB
M5 · 32 GBUD-IQ1_SToo big145 GB
M5 Pro · 24 GBUD-IQ1_SToo big145 GB
M5 Pro · 48 GBUD-IQ1_SToo big145 GB
M5 Pro · 64 GBUD-IQ1_SToo big145 GB
M5 Max · 36 GBUD-IQ1_SToo big145 GB
M5 Max · 48 GBUD-IQ1_SToo big145 GB
M5 Max · 64 GBUD-IQ1_SToo big145 GB
M5 Max · 128 GBUD-IQ1_SToo big145 GB
M5 Ultra · 96 GBUD-IQ1_SToo big145 GB
M5 Ultra · 256 GBUD-IQ1_MRuns great174 GB35
M5 Ultra · 512 GBQ4_K_MRuns well410 GB18
M4 · 16 GBUD-IQ1_SToo big145 GB
M4 · 24 GBUD-IQ1_SToo big145 GB
M4 · 32 GBUD-IQ1_SToo big145 GB
M4 Pro · 24 GBUD-IQ1_SToo big145 GB
M4 Pro · 48 GBUD-IQ1_SToo big145 GB
M4 Pro · 64 GBUD-IQ1_SToo big145 GB
M4 Max · 36 GBUD-IQ1_SToo big145 GB
M4 Max · 48 GBUD-IQ1_SToo big145 GB
M4 Max · 64 GBUD-IQ1_SToo big145 GB
M4 Max · 96 GBUD-IQ1_SToo big145 GB
M4 Max · 128 GBUD-IQ1_SToo big145 GB
M3 · 8 GBUD-IQ1_SToo big145 GB
M3 · 16 GBUD-IQ1_SToo big145 GB
M3 · 24 GBUD-IQ1_SToo big145 GB
M3 Pro · 18 GBUD-IQ1_SToo big145 GB
M3 Pro · 36 GBUD-IQ1_SToo big145 GB
M3 Max · 36 GBUD-IQ1_SToo big145 GB
M3 Max · 48 GBUD-IQ1_SToo big145 GB
M3 Max · 64 GBUD-IQ1_SToo big145 GB
M3 Max · 96 GBUD-IQ1_SToo big145 GB
M3 Max · 128 GBUD-IQ1_SToo big145 GB
M3 Ultra · 96 GBUD-IQ1_SToo big145 GB
M3 Ultra · 256 GBUD-IQ1_MRuns great174 GB19
M3 Ultra · 512 GBQ4_K_MRuns well410 GB11
M2 · 8 GBUD-IQ1_SToo big145 GB
M2 · 16 GBUD-IQ1_SToo big145 GB
M2 · 24 GBUD-IQ1_SToo big145 GB
M2 Pro · 16 GBUD-IQ1_SToo big145 GB
M2 Pro · 32 GBUD-IQ1_SToo big145 GB
M2 Max · 32 GBUD-IQ1_SToo big145 GB
M2 Max · 64 GBUD-IQ1_SToo big145 GB
M2 Max · 96 GBUD-IQ1_SToo big145 GB
M2 Ultra · 64 GBUD-IQ1_SToo big145 GB
M2 Ultra · 128 GBUD-IQ1_SToo big145 GB
M2 Ultra · 192 GBUD-IQ1_SRuns well145 GB21
M1 · 8 GBUD-IQ1_SToo big145 GB
M1 · 16 GBUD-IQ1_SToo big145 GB
M1 Pro · 16 GBUD-IQ1_SToo big145 GB
M1 Pro · 32 GBUD-IQ1_SToo big145 GB
M1 Max · 32 GBUD-IQ1_SToo big145 GB
M1 Max · 64 GBUD-IQ1_SToo big145 GB
M1 Ultra · 64 GBUD-IQ1_SToo big145 GB
M1 Ultra · 128 GBUD-IQ1_SToo big145 GB

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
DeepSeek
Released
January 2025
Parameters
671B, 38B active
Longest chat
160K tokens
Reads pictures
No
Licence
mit
Downloads this month
41,037
Likes
1,141
Sizes
13, 140 to 1342 GB
Kind
Community version

Badge for the model card

Shows on DeepSeek R1'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