Outmake Models
Models

Ling 3.0 Flash

Ant Group · August 2026

Get Hugging Face

A 127B, 5.6B active chat model from Ant Group.

Rating
3.1
Downloads
337K
Likes
116
Parameters
127B, 5.6B active
Context
256K
Licence
mit

Too big for this Mac

Its smallest size needs 21 GB of memory, more than M4 · 16 GB can give it.

Ratings

3.1 out of 5, across the tests below.

Expert questionsHumanity's Last Exam
22.7%
MathsAIME 2026
93.2%

Humanity's Last Exam: questions written to be beyond today's models. AIME 2026: this year's AIME competition problems. 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.

Ling 3.0 Flash runs well from a Mac with an M1 Pro and 32 GB of memory. 40 of 59 Mac configurations run it well.

Compare with

The nearest models in size.

Sizes

From bartowski/Ling-3.0-flash-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.

SizeDownloadMemory at 8KGet
IQ1_S28 GB28 GBestimatedOpen
IQ1_M31 GB31 GBestimatedOpen
IQ2_XXS35 GB35 GBestimatedOpen
IQ2_XS39 GB39 GBestimatedOpen
IQ2_S40 GB40 GBestimatedOpen
IQ2_M44 GB44 GBestimatedOpen
Q2_K46 GB46 GBestimatedOpen
Q2_K_L46 GB46 GBestimatedOpen
IQ3_XXS54 GB54 GBestimatedOpen
Q3_K_S56 GB56 GBestimatedOpen
IQ3_XS59 GB59 GBestimatedOpen
Q3_K_M59 GB59 GBestimatedOpen
Q3_K_L61 GB62 GBestimatedOpen
IQ3_M62 GB62 GBestimatedOpen
Q3_K_XL62 GB62 GBestimatedOpen
IQ4_XS69 GB69 GBestimatedOpen
IQ4_NL73 GB73 GBestimatedOpen
Q4_073 GB73 GBestimatedOpen
Q4_K_S75 GB75 GBestimatedOpen
Q4_K_M78 GB78 GBestimatedOpen
Q4_K_L78 GB78 GBestimatedOpen
Q4_180 GB80 GBestimatedOpen
Q5_K_S88 GB88 GBestimatedOpen
Q5_K_M91 GB91 GBestimatedOpen
Q5_K_L91 GB91 GBestimatedOpen
Q6_K109 GB109 GBestimatedOpen
Q8_0136 GB136 GBestimatedOpen
BF16255 GB255 GBestimatedOpen

Run It Anywhere

Ling 3.0 Flash is an open model, so any app that runs GGUF files can run it. These take the IQ1_S size from bartowski straight from Hugging Face.

  • LM StudioMac, Windows, LinuxOpen
  • JanMac, Windows, LinuxOpen
  • MstyMac, Windows, LinuxOpen
  • OllamaMac, Windows, Linuxollama run hf.co/bartowski/Ling-3.0-flash-GGUF:IQ1_S
  • llama.cppMac, Windows, Linuxllama-server -hf bartowski/Ling-3.0-flash-GGUF:IQ1_S
  • Docker Model RunnerMac, Windows, Linuxdocker model run hf.co/bartowski/Ling-3.0-flash-GGUF:IQ1_S
On a PC Graphics Card
Video memoryLargest size that fitsDownloadMemory at 8K
6 GBNone worth runningneeds 54 GB
8 GBNone worth runningneeds 54 GB
10 GBNone worth runningneeds 54 GB
11 GBNone worth runningneeds 54 GB
12 GBNone worth runningneeds 54 GB
16 GBNone worth runningneeds 54 GB
20 GBNone worth runningneeds 54 GB
24 GBNone worth runningneeds 54 GB
32 GBNone worth runningneeds 54 GB
48 GBNone worth runningneeds 54 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 GBQ1_0Too big21 GB
M6 · 24 GBQ1_0Too big21 GB
M6 · 32 GBQ1_0Runs well21 GB51
M5 · 16 GBQ1_0Too big21 GB
M5 · 24 GBQ1_0Too big21 GB
M5 · 32 GBQ1_0Runs well21 GB51
M5 Pro · 24 GBQ1_0Too big21 GB
M5 Pro · 48 GBQ1_0Runs great21 GB87
M5 Pro · 64 GBIQ1_MRuns great31 GB59
M5 Max · 36 GBQ1_0Runs well21 GB114
M5 Max · 48 GBQ1_0Runs great21 GB135
M5 Max · 64 GBIQ1_MRuns great31 GB96
M5 Max · 128 GBIQ4_XS_FLATRuns great69 GB58
M5 Ultra · 96 GBIQ4_XS_FLATRuns well69 GB95
M5 Ultra · 256 GBQ8_0Runs great137 GB72
M5 Ultra · 512 GBQ8_0Runs great137 GB72
M4 · 16 GBQ1_0Too big21 GB
M4 · 24 GBQ1_0Too big21 GB
M4 · 32 GBQ1_0Runs well21 GB30
M4 Pro · 24 GBQ1_0Too big21 GB
M4 Pro · 48 GBQ1_0Runs great21 GB46
M4 Pro · 64 GBIQ1_MRuns great31 GB34
M4 Max · 36 GBQ1_0Runs well21 GB53
M4 Max · 48 GBQ1_0Runs great21 GB58
M4 Max · 64 GBIQ1_MRuns great31 GB46
M4 Max · 96 GBIQ4_XS_FLATRuns well69 GB29
M4 Max · 128 GBIQ4_XS_FLATRuns great69 GB34
M3 · 8 GBQ1_0Too big21 GB
M3 · 16 GBQ1_0Too big21 GB
M3 · 24 GBQ1_0Too big21 GB
M3 Pro · 18 GBQ1_0Too big21 GB
M3 Pro · 36 GBQ1_0Runs well21 GB37
M3 Max · 36 GBQ1_0Runs well21 GB53
M3 Max · 48 GBQ1_0Runs great21 GB59
M3 Max · 64 GBIQ1_MRuns great31 GB45
M3 Max · 96 GBIQ4_XS_FLATRuns well69 GB26
M3 Max · 128 GBIQ4_XS_FLATRuns great69 GB31
M3 Ultra · 96 GBIQ4_XS_FLATRuns well69 GB45
M3 Ultra · 256 GBQ8_0Runs great137 GB37
M3 Ultra · 512 GBQ8_0Runs great137 GB37
M2 · 8 GBQ1_0Too big21 GB
M2 · 16 GBQ1_0Too big21 GB
M2 · 24 GBQ1_0Too big21 GB
M2 Pro · 16 GBQ1_0Too big21 GB
M2 Pro · 32 GBQ1_0Runs well21 GB43
M2 Max · 32 GBQ1_0Runs well21 GB58
M2 Max · 64 GBIQ1_MRuns great31 GB45
M2 Max · 96 GBIQ4_XS_FLATRuns well69 GB31
M2 Ultra · 64 GBIQ1_MRuns great31 GB57
M2 Ultra · 128 GBIQ4_XS_FLATRuns great69 GB44
M2 Ultra · 192 GBQ6_KRuns great111 GB36
M1 · 8 GBQ1_0Too big21 GB
M1 · 16 GBQ1_0Too big21 GB
M1 Pro · 16 GBQ1_0Too big21 GB
M1 Pro · 32 GBQ1_0Runs well21 GB33
M1 Max · 32 GBQ1_0Runs well21 GB41
M1 Max · 64 GBIQ1_MRuns great31 GB33
M1 Ultra · 64 GBIQ1_MRuns great31 GB39
M1 Ultra · 128 GBIQ4_XS_FLATRuns great69 GB33

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

Packaged by

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

Information

Maker
Ant Group
Released
August 2026
Parameters
127B, 5.6B active
Longest chat
256K tokens
Reads pictures
No
Licence
mit
Downloads this month
337,484
Likes
116
Sizes
28, 28 to 255 GB
Kind
Maker's release

Badge for the model card

Shows on Ling 3.0 Flash'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