Outmake Models
Models

Qwen2.5 14B

Alibaba Qwen · September 2024

Get Hugging Face

A 15B chat model from Alibaba Qwen.

Downloads
258K
Likes
179
Parameters
15B
Context
32K
Licence
apache-2.0

Runs well on M4 · 16 GB

The Q4_1 size from ThomasBaruzier is the one to get: a 9.4 GB download that uses 10 GB of memory, and writes about 4.9 words a second.

Qwen2.5 14B runs well from a Mac with an M1 and 8 GB of memory. 59 of 59 Mac configurations run it well.

Compare with

The nearest models in size.

Sizes

From ThomasBaruzier/Qwen2.5-14B-Instruct-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.

SizeDownloadMemory at 8KGet
IQ1_S3.6 GB4.6 GBestimatedOpen
IQ1_M3.9 GB4.9 GBestimatedOpen
IQ2_XXS4.3 GB5.4 GBestimatedOpen
IQ2_XS4.7 GB5.7 GBestimatedOpen
IQ2_S5.0 GB6.0 GBestimatedOpen
IQ2_M5.4 GB6.4 GBestimatedOpen
Q2_K_S5.4 GB6.4 GBestimatedOpen
Q2_K5.8 GB6.8 GBestimatedOpen
IQ3_XXS5.9 GB7.0 GBestimatedOpen
IQ3_XS6.4 GB7.4 GBestimatedOpen
Q3_K_S6.7 GB7.7 GBestimatedOpen
IQ3_S6.7 GB7.7 GBestimatedOpen
IQ3_M6.9 GB8.0 GBestimatedOpen
Q3_K_M7.3 GB8.4 GBestimatedOpen
Q3_K_L7.9 GB9.0 GBestimatedOpen
IQ4_XS8.1 GB9.2 GBestimatedOpen
Q4_0_4_48.5 GB9.6 GBestimatedOpen
Q4_0_4_88.5 GB9.6 GBestimatedOpen
Q4_0_8_88.5 GB9.6 GBestimatedOpen
Q4_08.5 GB9.6 GBestimatedOpen
IQ4_NL8.5 GB9.6 GBestimatedOpen
Q4_K_S8.6 GB9.6 GBestimatedOpen
Q4_K_M9.0 GB10 GBestimatedOpen
Q4_19.4 GB10 GBestimatedOpen
Q5_K_S10 GB11 GBestimatedOpen
Q5_010 GB11 GBestimatedOpen
Q5_K_M11 GB12 GBestimatedOpen
Q5_111 GB12 GBestimatedOpen
Q6_K12 GB13 GBestimatedOpen
Q8_016 GB17 GBestimatedOpen
F1630 GB31 GBestimatedOpen

Run It Anywhere

Qwen2.5 14B is an open model, so any app that runs GGUF files can run it. These take the Q4_1 size from ThomasBaruzier straight from Hugging Face.

  • LM StudioMac, Windows, LinuxOpen
  • JanMac, Windows, LinuxOpen
  • MstyMac, Windows, LinuxOpen
  • OllamaMac, Windows, Linuxollama run hf.co/ThomasBaruzier/Qwen2.5-14B-Instruct-GGUF:Q4_1
  • llama.cppMac, Windows, Linuxllama-server -hf ThomasBaruzier/Qwen2.5-14B-Instruct-GGUF:Q4_1
  • Docker Model RunnerMac, Windows, Linuxdocker model run hf.co/ThomasBaruzier/Qwen2.5-14B-Instruct-GGUF:Q4_1
On a PC Graphics Card
Video memoryLargest size that fitsDownloadMemory at 8K
6 GBNone worth runningneeds 7.0 GB
8 GBIQ3_S6.7 GB7.7 GB
10 GBQ4_K_S8.6 GB9.6 GB
11 GBQ4_19.4 GB10 GB
12 GBQ5_K_M11 GB12 GB
16 GBQ6_K12 GB13 GB
20 GBQ8_016 GB17 GB
24 GBQ8_016 GB17 GB
32 GBF1630 GB31 GB
48 GBF1630 GB31 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 GBQ4_1Runs well10 GB6.9
M6 · 24 GBQ5_K_MRuns great12 GB5.7
M6 · 32 GBQ6_KRuns great14 GB5.4
M5 · 16 GBQ4_1Runs well10 GB6.3
M5 · 24 GBQ5_K_MRuns great12 GB5.2
M5 · 32 GBQ6_KRuns great14 GB4.9
M5 Pro · 24 GBQ5_K_MRuns great12 GB10
M5 Pro · 48 GBQ8_0Runs great20 GB9.3
M5 Pro · 64 GBQ8_0Runs great20 GB9.3
M5 Max · 36 GBQ8_0Runs great17 GB14
M5 Max · 48 GBQ8_0Runs great20 GB18
M5 Max · 64 GBQ8_0Runs great20 GB18
M5 Max · 128 GBQ8_0Runs great20 GB18
M5 Ultra · 96 GBQ8_0Runs great20 GB35
M5 Ultra · 256 GBQ8_0Runs great20 GB35
M5 Ultra · 512 GBQ8_0Runs great20 GB35
M4 · 16 GBQ4_1Runs well10 GB4.9
M4 · 24 GBQ5_K_MRuns great12 GB4
M4 · 32 GBQ6_KRuns great14 GB3.7
M4 Pro · 24 GBQ5_K_MRuns great12 GB8.7
M4 Pro · 48 GBQ8_0Runs great20 GB7.7
M4 Pro · 64 GBQ8_0Runs great20 GB7.7
M4 Max · 36 GBQ8_0Runs great17 GB11
M4 Max · 48 GBQ8_0Runs great20 GB14
M4 Max · 64 GBQ8_0Runs great20 GB14
M4 Max · 96 GBQ8_0Runs great20 GB11
M4 Max · 128 GBQ8_0Runs great20 GB14
M3 · 8 GBIQ1_MRuns well4.9 GB5.5
M3 · 16 GBQ4_1Runs well10 GB4.1
M3 · 24 GBQ5_K_MRuns great12 GB3.4
M3 Pro · 18 GBQ3_K_MRuns great8.4 GB6.1
M3 Pro · 36 GBQ8_0Runs great17 GB4.4
M3 Max · 36 GBQ8_0Runs great17 GB8.6
M3 Max · 48 GBQ8_0Runs great20 GB11
M3 Max · 64 GBQ8_0Runs great20 GB11
M3 Max · 96 GBQ8_0Runs great20 GB8.6
M3 Max · 128 GBQ8_0Runs great20 GB11
M3 Ultra · 96 GBQ8_0Runs great20 GB20
M3 Ultra · 256 GBQ8_0Runs great20 GB20
M3 Ultra · 512 GBQ8_0Runs great20 GB20
M2 · 8 GBIQ1_MRuns well4.9 GB5.5
M2 · 16 GBQ4_1Runs well10 GB4.1
M2 · 24 GBQ5_K_MRuns great12 GB3.4
M2 Pro · 16 GBQ4_1Runs well10 GB8
M2 Pro · 32 GBQ6_KRuns great14 GB6.1
M2 Max · 32 GBQ6_KRuns great14 GB11
M2 Max · 64 GBQ8_0Runs great20 GB11
M2 Max · 96 GBQ8_0Runs great20 GB11
M2 Ultra · 64 GBQ8_0Runs great20 GB20
M2 Ultra · 128 GBQ8_0Runs great20 GB20
M2 Ultra · 192 GBQ8_0Runs great20 GB20
M1 · 8 GBIQ1_MRuns well4.9 GB3.7
M1 · 16 GBQ4_1Runs well10 GB2.8
M1 Pro · 16 GBQ4_1Runs well10 GB7.7
M1 Pro · 32 GBQ6_KRuns great14 GB5.8
M1 Max · 32 GBQ6_KRuns great14 GB11
M1 Max · 64 GBQ8_0Runs great20 GB10
M1 Ultra · 64 GBQ8_0Runs great20 GB18
M1 Ultra · 128 GBQ8_0Runs great20 GB18

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

Packaged by

8 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
15B
Longest chat
32K tokens
Reads pictures
No
Licence
apache-2.0
Downloads this month
257,602
Likes
179
Sizes
31, 3.6 to 30 GB
Kind
Maker's release

Badge for the model card

Shows on Qwen2.5 14B'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