Outmake Models
Models

Hunyuan A13B

Tencent · July 2025

Get Hugging Face

A 80B, 13B active chat model from Tencent.

Downloads
3.2K
Likes
48
Parameters
80B, 13B active
Context
256K
Licence
other

Too big for this Mac

Its smallest size needs 42 GB of memory, more than M4 · 16 GB can give it.

Ratings

KnowledgeMMLU-Pro
67.3%

MMLU-Pro: graduate-level questions in 14 subjects. 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.

Hunyuan A13B 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 unsloth/Hunyuan-A13B-Instruct-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.

SizeDownloadMemory at 8KGet
UD-TQ1_022 GB23 GBestimatedOpen
UD-IQ1_S25 GB25 GBestimatedOpen
UD-IQ1_M26 GB26 GBestimatedOpen
UD-IQ2_XXS28 GB28 GBestimatedOpen
UD-IQ2_M29 GB30 GBestimatedOpen
Q2_K29 GB30 GBestimatedOpen
Q2_K_L29 GB30 GBestimatedOpen
UD-Q2_K_XL31 GB32 GBestimatedOpen
UD-IQ3_XXS34 GB35 GBestimatedOpen
Q3_K_S35 GB36 GBestimatedOpen
UD-Q3_K_XL36 GB37 GBestimatedOpen
Q3_K_M39 GB39 GBestimatedOpen
IQ4_XS43 GB44 GBestimatedOpen
IQ4_NL45 GB46 GBestimatedOpen
Q4_046 GB46 GBestimatedOpen
Q4_K_S46 GB47 GBestimatedOpen
UD-Q4_K_XL47 GB47 GBestimatedOpen
Q4_K_M49 GB50 GBestimatedOpen
Q4_150 GB51 GBestimatedOpen
Q5_K_S55 GB56 GBestimatedOpen
Q5_K_M57 GB58 GBestimatedOpen
UD-Q5_K_XL58 GB58 GBestimatedOpen
UD-Q6_K_XL70 GB71 GBestimatedOpen
Q8_085 GB86 GBestimatedOpen
UD-Q8_K_XL98 GB99 GBestimatedOpen
BF16161 GB162 GBestimatedOpen

Run It Anywhere

Hunyuan A13B is an open model, so any app that runs GGUF files can run it. These take the UD-TQ1_0 size from unsloth straight from Hugging Face.

  • LM StudioMac, Windows, LinuxOpen
  • JanMac, Windows, LinuxOpen
  • MstyMac, Windows, LinuxOpen
  • OllamaMac, Windows, Linuxollama run hf.co/unsloth/Hunyuan-A13B-Instruct-GGUF:UD-TQ1_0
  • llama.cppMac, Windows, Linuxllama-server -hf unsloth/Hunyuan-A13B-Instruct-GGUF:UD-TQ1_0
  • Docker Model RunnerMac, Windows, Linuxdocker model run hf.co/unsloth/Hunyuan-A13B-Instruct-GGUF:UD-TQ1_0
On a PC Graphics Card
Video memoryLargest size that fitsDownloadMemory at 8K
6 GBNone worth runningneeds 30 GB
8 GBNone worth runningneeds 30 GB
10 GBNone worth runningneeds 30 GB
11 GBNone worth runningneeds 30 GB
12 GBNone worth runningneeds 30 GB
16 GBNone worth runningneeds 30 GB
20 GBNone worth runningneeds 30 GB
24 GBNone worth runningneeds 30 GB
32 GBUD-IQ2_M29 GB30 GB
48 GBQ4_K_S46 GB47 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-TQ1_0Too big42 GB
M6 · 24 GBUD-TQ1_0Too big42 GB
M6 · 32 GBUD-TQ1_0Tight fit25 GB8.6
M5 · 16 GBUD-TQ1_0Too big42 GB
M5 · 24 GBUD-TQ1_0Too big42 GB
M5 · 32 GBUD-TQ1_0Tight fit25 GB7.8
M5 Pro · 24 GBUD-TQ1_0Too big42 GB
M5 Pro · 48 GBUD-Q2_K_XLRuns well32 GB13
M5 Pro · 64 GBQ2_KRuns great31 GB14
M5 Max · 36 GBUD-TQ1_0Runs well24 GB23
M5 Max · 48 GBUD-Q2_K_XLRuns well32 GB25
M5 Max · 64 GBQ2_KRuns great31 GB26
M5 Max · 128 GBUD-Q5_K_XLRuns great68 GB18
M5 Ultra · 96 GBQ4_0Runs great46 GB44
M5 Ultra · 256 GBQ8_0Runs great105 GB31
M5 Ultra · 512 GBQ8_0Runs great105 GB31
M4 · 16 GBUD-TQ1_0Too big42 GB
M4 · 24 GBUD-TQ1_0Too big42 GB
M4 · 32 GBUD-TQ1_0Tight fit25 GB6
M4 Pro · 24 GBUD-TQ1_0Too big42 GB
M4 Pro · 48 GBUD-Q2_K_XLRuns well32 GB11
M4 Pro · 64 GBQ2_KRuns great31 GB11
M4 Max · 36 GBUD-TQ1_0Runs well24 GB18
M4 Max · 48 GBUD-Q2_K_XLRuns well32 GB20
M4 Max · 64 GBQ2_KRuns great31 GB20
M4 Max · 96 GBQ4_0Runs great46 GB15
M4 Max · 128 GBUD-Q5_K_XLRuns great68 GB14
M3 · 8 GBUD-TQ1_0Too big42 GB
M3 · 16 GBUD-TQ1_0Too big42 GB
M3 · 24 GBUD-TQ1_0Too big42 GB
M3 Pro · 18 GBUD-TQ1_0Too big42 GB
M3 Pro · 36 GBUD-TQ1_0Runs well24 GB7.5
M3 Max · 36 GBUD-TQ1_0Runs well24 GB14
M3 Max · 48 GBUD-Q2_K_XLRuns well32 GB16
M3 Max · 64 GBQ2_KRuns great31 GB16
M3 Max · 96 GBQ4_0Runs great46 GB11
M3 Max · 128 GBUD-Q5_K_XLRuns great68 GB11
M3 Ultra · 96 GBQ4_0Runs great46 GB26
M3 Ultra · 256 GBQ8_0Runs great105 GB18
M3 Ultra · 512 GBQ8_0Runs great105 GB18
M2 · 8 GBUD-TQ1_0Too big42 GB
M2 · 16 GBUD-TQ1_0Too big42 GB
M2 · 24 GBUD-TQ1_0Too big42 GB
M2 Pro · 16 GBUD-TQ1_0Too big42 GB
M2 Pro · 32 GBUD-TQ1_0Tight fit25 GB9.7
M2 Max · 32 GBUD-TQ1_0Tight fit25 GB18
M2 Max · 64 GBQ2_KRuns great31 GB16
M2 Max · 96 GBQ4_0Runs great46 GB15
M2 Ultra · 64 GBQ2_KRuns great31 GB28
M2 Ultra · 128 GBUD-Q5_K_XLRuns great68 GB20
M2 Ultra · 192 GBQ8_0Runs great105 GB18
M1 · 8 GBUD-TQ1_0Too big42 GB
M1 · 16 GBUD-TQ1_0Too big42 GB
M1 Pro · 16 GBUD-TQ1_0Too big42 GB
M1 Pro · 32 GBUD-TQ1_0Tight fit25 GB9.2
M1 Max · 32 GBUD-TQ1_0Tight fit25 GB16
M1 Max · 64 GBQ2_KRuns great31 GB15
M1 Ultra · 64 GBQ2_KRuns great31 GB24
M1 Ultra · 128 GBUD-Q5_K_XLRuns great68 GB18

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

Information

Maker
Tencent
Released
July 2025
Parameters
80B, 13B active
Longest chat
256K tokens
Reads pictures
No
Licence
other
Downloads this month
3,226
Likes
48
Sizes
26, 22 to 161 GB
Kind
Maker's release

Badge for the model card

Shows on Hunyuan A13B'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