Outmake Models
Models

Qwen2.5 32B

Alibaba Qwen · September 2024

Get Hugging Face

A 33B chat model from Alibaba Qwen.

Downloads
833K
Likes
158
Parameters
33B
Context
32K
Licence
apache-2.0

Runs well on M4 · 16 GB

The IQ2_XXS size from ThomasBaruzier is the one to get: a 9.0 GB download that uses 10 GB of memory, and writes about 3.8 words a second.

Qwen2.5 32B 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 ThomasBaruzier/Qwen2.5-32B-Instruct-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.

SizeDownloadMemory at 8KGet
IQ1_S7.3 GB8.6 GBestimatedOpen
IQ1_M7.9 GB9.3 GBestimatedOpen
IQ2_XXS9.0 GB10 GBestimatedOpen
IQ2_XS10.0 GB11 GBestimatedOpen
IQ2_S10 GB12 GBestimatedOpen
IQ2_M11 GB13 GBestimatedOpen
Q2_K_S11 GB13 GBestimatedOpen
Q2_K12 GB14 GBestimatedOpen
IQ3_XXS13 GB14 GBestimatedOpen
IQ3_XS14 GB15 GBestimatedOpen
Q3_K_S14 GB16 GBestimatedOpen
IQ3_S14 GB16 GBestimatedOpen
IQ3_M15 GB16 GBestimatedOpen
Q3_K_M16 GB17 GBestimatedOpen
Q3_K_L17 GB19 GBestimatedOpen
IQ4_XS18 GB19 GBestimatedOpen
Q4_0_4_419 GB20 GBestimatedOpen
Q4_0_4_819 GB20 GBestimatedOpen
Q4_0_8_819 GB20 GBestimatedOpen
IQ4_NL19 GB20 GBestimatedOpen
Q4_019 GB20 GBestimatedOpen
Q4_K_S19 GB20 GBestimatedOpen
Q4_K_M20 GB21 GBestimatedOpen
Q4_121 GB22 GBestimatedOpen
Q5_K_S23 GB24 GBestimatedOpen
Q5_023 GB24 GBestimatedOpen
Q5_K_M23 GB25 GBestimatedOpen
Q5_125 GB26 GBestimatedOpen
Q6_K27 GB28 GBestimatedOpen
Q8_035 GB36 GBestimatedOpen
F1666 GB67 GBestimatedOpen

Run It Anywhere

Qwen2.5 32B is an open model, so any app that runs GGUF files can run it. These take the IQ2_XXS size from ThomasBaruzier straight from Hugging Face.

  • LM StudioMac, Windows, LinuxOpen
  • JanMac, Windows, LinuxOpen
  • MstyMac, Windows, LinuxOpen
  • OllamaMac, Windows, Linuxollama run hf.co/ThomasBaruzier/Qwen2.5-32B-Instruct-GGUF:IQ2_XXS
  • llama.cppMac, Windows, Linuxllama-server -hf ThomasBaruzier/Qwen2.5-32B-Instruct-GGUF:IQ2_XXS
  • Docker Model RunnerMac, Windows, Linuxdocker model run hf.co/ThomasBaruzier/Qwen2.5-32B-Instruct-GGUF:IQ2_XXS
On a PC Graphics Card
Video memoryLargest size that fitsDownloadMemory at 8K
6 GBNone worth runningneeds 14 GB
8 GBNone worth runningneeds 14 GB
10 GBNone worth runningneeds 14 GB
11 GBNone worth runningneeds 14 GB
12 GBNone worth runningneeds 14 GB
16 GBIQ3_S14 GB16 GB
20 GBIQ4_XS18 GB19 GB
24 GBQ4_121 GB22 GB
32 GBQ6_K27 GB28 GB
48 GBQ8_035 GB36 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 GBIQ2_XXSRuns well10 GB5.5
M6 · 24 GBIQ3_SRuns well16 GB4.2
M6 · 32 GBQ4_K_MRuns well21 GB3.4
M5 · 16 GBIQ2_XXSRuns well10 GB5
M5 · 24 GBIQ3_SRuns well16 GB3.8
M5 · 32 GBQ4_K_MRuns well21 GB3.1
M5 Pro · 24 GBIQ3_SRuns well16 GB7.5
M5 Pro · 48 GBQ4_1Runs great22 GB6.7
M5 Pro · 64 GBQ6_KRuns great29 GB5.1
M5 Max · 36 GBQ4_1Runs well23 GB10
M5 Max · 48 GBQ4_1Runs great22 GB13
M5 Max · 64 GBQ6_KRuns great29 GB10
M5 Max · 128 GBQ8_0Runs great40 GB9.4
M5 Ultra · 96 GBQ8_0Runs great40 GB18
M5 Ultra · 256 GBQ8_0Runs great40 GB18
M5 Ultra · 512 GBQ8_0Runs great40 GB18
M4 · 16 GBIQ2_XXSRuns well10 GB3.8
M4 · 24 GBIQ3_SRuns well16 GB3
M4 · 32 GBQ4_K_MRuns well21 GB2.4
M4 Pro · 24 GBIQ3_SRuns well16 GB6.4
M4 Pro · 48 GBQ4_1Runs great22 GB5.8
M4 Pro · 64 GBQ6_KRuns great29 GB4.3
M4 Max · 36 GBQ4_1Runs well23 GB8.4
M4 Max · 48 GBQ4_1Runs great22 GB11
M4 Max · 64 GBQ6_KRuns great29 GB8.1
M4 Max · 96 GBQ8_0Runs great40 GB5.9
M4 Max · 128 GBQ8_0Runs great40 GB7.7
M3 · 8 GBIQ1_SToo big12 GB
M3 · 16 GBIQ2_XXSRuns well10 GB3.3
M3 · 24 GBIQ3_SRuns well16 GB2.5
M3 Pro · 18 GBIQ1_SRuns great8.6 GB5.3
M3 Pro · 36 GBQ4_1Runs well23 GB3.4
M3 Max · 36 GBQ4_1Runs well23 GB6.5
M3 Max · 48 GBQ4_1Runs great22 GB8.4
M3 Max · 64 GBQ6_KRuns great29 GB6.2
M3 Max · 96 GBQ8_0Runs great40 GB4.5
M3 Max · 128 GBQ8_0Runs great40 GB5.8
M3 Ultra · 96 GBQ8_0Runs great40 GB11
M3 Ultra · 256 GBQ8_0Runs great40 GB11
M3 Ultra · 512 GBQ8_0Runs great40 GB11
M2 · 8 GBIQ1_SToo big12 GB
M2 · 16 GBIQ2_XXSRuns well10 GB3.3
M2 · 24 GBIQ3_SRuns well16 GB2.5
M2 Pro · 16 GBIQ2_XXSRuns well10 GB6.3
M2 Pro · 32 GBQ4_K_MRuns well21 GB4
M2 Max · 32 GBQ4_K_MRuns well21 GB7.6
M2 Max · 64 GBQ6_KRuns great29 GB6.2
M2 Max · 96 GBQ8_0Runs great40 GB5.8
M2 Ultra · 64 GBQ6_KRuns great29 GB11
M2 Ultra · 128 GBQ8_0Runs great40 GB11
M2 Ultra · 192 GBQ8_0Runs great40 GB11
M1 · 8 GBIQ1_SToo big12 GB
M1 · 16 GBIQ2_XXSRuns well10 GB2.2
M1 Pro · 16 GBIQ2_XXSRuns well10 GB5.9
M1 Pro · 32 GBQ4_K_MRuns well21 GB3.9
M1 Max · 32 GBQ4_K_MRuns well21 GB7.1
M1 Max · 64 GBQ6_KRuns great29 GB5.9
M1 Ultra · 64 GBQ6_KRuns great29 GB10
M1 Ultra · 128 GBQ8_0Runs great40 GB10

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

Packaged by

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

Information

Maker
Alibaba Qwen
Released
September 2024
Parameters
33B
Longest chat
32K tokens
Reads pictures
No
Licence
apache-2.0
Downloads this month
833,083
Likes
158
Sizes
31, 7.3 to 66 GB
Kind
Maker's release

Badge for the model card

Shows on Qwen2.5 32B'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