Outmake Models
Models

Ling Flash 2.0

Ant Group · September 2025

Get Hugging Face

A 103B, 6.2B active chat model from Ant Group.

Rating
3.4
Downloads
4.8K
Likes
6
Parameters
103B, 6.2B active
Context
32K
Licence
mit

Too big for this Mac

Its smallest size needs 23 GB of memory, more than M4 · 16 GB can give it.

Ratings

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

Text
1343
Coding
1409

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.

Ling Flash 2.0 runs well from a Mac with an M3 Pro and 36 GB of memory. 33 of 59 Mac configurations run it well.

Compare with

The nearest models in size.

Sizes

From bartowski/inclusionAI_Ling-flash-2.0-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.

SizeDownloadMemory at 8KGet
IQ1_S21 GB22 GBestimatedOpen
IQ1_M22 GB23 GBestimatedOpen
IQ2_XXS26 GB26 GBestimatedOpen
IQ2_XS29 GB29 GBestimatedOpen
IQ2_S29 GB29 GBestimatedOpen
IQ2_M32 GB33 GBestimatedOpen
Q2_K36 GB37 GBestimatedOpen
Q2_K_L37 GB37 GBestimatedOpen
IQ3_XXS41 GB41 GBestimatedOpen
IQ3_XS42 GB43 GBestimatedOpen
Q3_K_S45 GB45 GBestimatedOpen
IQ3_M47 GB48 GBestimatedOpen
Q3_K_M47 GB48 GBestimatedOpen
Q3_K_L49 GB49 GBestimatedOpen
Q3_K_XL50 GB50 GBestimatedOpen
IQ4_XS55 GB56 GBestimatedOpen
IQ4_NL58 GB59 GBestimatedOpen
Q4_059 GB60 GBestimatedOpen
Q4_K_S60 GB61 GBestimatedOpen
Q4_K_M63 GB63 GBestimatedOpen
Q4_K_L63 GB64 GBestimatedOpen
Q4_165 GB65 GBestimatedOpen
Q5_K_S71 GB71 GBestimatedOpen
Q5_K_M73 GB74 GBestimatedOpen
Q6_K85 GB85 GBestimatedOpen
Q8_0109 GB110 GBestimatedOpen

Run It Anywhere

Ling Flash 2.0 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/inclusionAI_Ling-flash-2.0-GGUF:IQ1_S
  • llama.cppMac, Windows, Linuxllama-server -hf bartowski/inclusionAI_Ling-flash-2.0-GGUF:IQ1_S
  • Docker Model RunnerMac, Windows, Linuxdocker model run hf.co/bartowski/inclusionAI_Ling-flash-2.0-GGUF:IQ1_S
On a PC Graphics Card
Video memoryLargest size that fitsDownloadMemory at 8K
6 GBNone worth runningneeds 41 GB
8 GBNone worth runningneeds 41 GB
10 GBNone worth runningneeds 41 GB
11 GBNone worth runningneeds 41 GB
12 GBNone worth runningneeds 41 GB
16 GBNone worth runningneeds 41 GB
20 GBNone worth runningneeds 41 GB
24 GBNone worth runningneeds 41 GB
32 GBNone worth runningneeds 41 GB
48 GBQ3_K_S45 GB45 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 GBIQ1_SToo big23 GB
M6 · 24 GBIQ1_SToo big23 GB
M6 · 32 GBIQ1_MTight fit24 GB19
M5 · 16 GBIQ1_SToo big23 GB
M5 · 24 GBIQ1_SToo big23 GB
M5 · 32 GBIQ1_MTight fit24 GB17
M5 Pro · 24 GBIQ1_SToo big23 GB
M5 Pro · 48 GBIQ1_MRuns great23 GB33
M5 Pro · 64 GBIQ3_XXSRuns well42 GB25
M5 Max · 36 GBIQ1_MRuns well24 GB48
M5 Max · 48 GBIQ1_MRuns great23 GB61
M5 Max · 64 GBIQ3_XXSRuns well42 GB48
M5 Max · 128 GBQ4_1Runs great66 GB42
M5 Ultra · 96 GBQ4_1Runs well66 GB77
M5 Ultra · 256 GBQ8_0Runs great111 GB58
M5 Ultra · 512 GBQ8_0Runs great111 GB58
M4 · 16 GBIQ1_SToo big23 GB
M4 · 24 GBIQ1_SToo big23 GB
M4 · 32 GBIQ1_MTight fit24 GB13
M4 Pro · 24 GBIQ1_SToo big23 GB
M4 Pro · 48 GBIQ1_MRuns great23 GB24
M4 Pro · 64 GBIQ3_XXSRuns well42 GB20
M4 Max · 36 GBIQ1_MRuns well24 GB32
M4 Max · 48 GBIQ1_MRuns great23 GB39
M4 Max · 64 GBIQ3_XXSRuns well42 GB32
M4 Max · 96 GBQ4_1Runs well66 GB25
M4 Max · 128 GBQ4_1Runs great66 GB31
M3 · 8 GBIQ1_SToo big23 GB
M3 · 16 GBIQ1_SToo big23 GB
M3 · 24 GBIQ1_SToo big23 GB
M3 Pro · 18 GBIQ1_SToo big23 GB
M3 Pro · 36 GBIQ1_MRuns well24 GB16
M3 Max · 36 GBIQ1_MRuns well24 GB27
M3 Max · 48 GBIQ1_MRuns great23 GB34
M3 Max · 64 GBIQ3_XXSRuns well42 GB27
M3 Max · 96 GBQ4_1Runs well66 GB20
M3 Max · 128 GBQ4_1Runs great66 GB25
M3 Ultra · 96 GBQ4_1Runs well66 GB42
M3 Ultra · 256 GBQ8_0Runs great111 GB32
M3 Ultra · 512 GBQ8_0Runs great111 GB32
M2 · 8 GBIQ1_SToo big23 GB
M2 · 16 GBIQ1_SToo big23 GB
M2 · 24 GBIQ1_SToo big23 GB
M2 Pro · 16 GBIQ1_SToo big23 GB
M2 Pro · 32 GBIQ1_MTight fit24 GB20
M2 Max · 32 GBIQ1_MTight fit24 GB33
M2 Max · 64 GBIQ3_XXSRuns well42 GB27
M2 Max · 96 GBQ4_1Runs well66 GB25
M2 Ultra · 64 GBIQ3_XXSRuns well42 GB44
M2 Ultra · 128 GBQ4_1Runs great66 GB42
M2 Ultra · 192 GBQ8_0Runs great111 GB32
M1 · 8 GBIQ1_SToo big23 GB
M1 · 16 GBIQ1_SToo big23 GB
M1 Pro · 16 GBIQ1_SToo big23 GB
M1 Pro · 32 GBIQ1_MTight fit24 GB18
M1 Max · 32 GBIQ1_MTight fit24 GB28
M1 Max · 64 GBIQ3_XXSRuns well42 GB23
M1 Ultra · 64 GBIQ3_XXSRuns well42 GB34
M1 Ultra · 128 GBQ4_1Runs great66 GB34

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

Information

Maker
Ant Group
Released
September 2025
Parameters
103B, 6.2B active
Longest chat
32K tokens
Reads pictures
No
Licence
mit
Downloads this month
4,839
Likes
6
Sizes
26, 21 to 109 GB
Kind
Maker's release

Badge for the model card

Shows on Ling Flash 2.0'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