Outmake Models
Models

Qwen 14B

Alibaba Qwen · September 2023

Get Hugging Face

A 14B chat model from Alibaba Qwen.

Rating
1.9
Downloads
1.1K
Likes
1
Parameters
14B
Context
8K

Runs well on M4 · 16 GB

The Q2_K size from mradermacher is the one to get: a 5.8 GB download that uses 9.8 GB of memory, and writes about 2.2 words a second.

Ratings

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

Text
1139
Coding
1198

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.

Qwen 14B 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 mradermacher/Qwen-14B-Chat-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.

SizeDownloadMemory at 8KGet
Q2_K5.8 GB9.8 GBestimatedOpen
Q3_K_S6.8 GB11 GBestimatedOpen
Q3_K_M7.7 GB12 GBestimatedOpen
IQ4_XS7.9 GB12 GBestimatedOpen
Q3_K_L8.0 GB12 GBestimatedOpen
Q4_K_S8.6 GB13 GBestimatedOpen
Q4_K_M9.4 GB13 GBestimatedOpen
Q5_K_S10 GB14 GBestimatedOpen
Q5_K_M11 GB15 GBestimatedOpen
Q6_K12 GB16 GBestimatedOpen
Q8_015 GB19 GBestimatedOpen

Run It Anywhere

Qwen 14B is an open model, so any app that runs GGUF files can run it. These take the Q2_K size from mradermacher straight from Hugging Face.

  • LM StudioMac, Windows, LinuxOpen
  • JanMac, Windows, LinuxOpen
  • MstyMac, Windows, LinuxOpen
  • OllamaMac, Windows, Linuxollama run hf.co/mradermacher/Qwen-14B-Chat-GGUF:Q2_K
  • llama.cppMac, Windows, Linuxllama-server -hf mradermacher/Qwen-14B-Chat-GGUF:Q2_K
  • Docker Model RunnerMac, Windows, Linuxdocker model run hf.co/mradermacher/Qwen-14B-Chat-GGUF:Q2_K
On a PC Graphics Card
Video memoryLargest size that fitsDownloadMemory at 8K
6 GBNone worth runningneeds 11 GB
8 GBNone worth runningneeds 11 GB
10 GBNone worth runningneeds 11 GB
11 GBQ3_K_S6.8 GB11 GB
12 GBQ3_K_M7.7 GB12 GB
16 GBQ5_K_M11 GB15 GB
20 GBQ8_015 GB19 GB
24 GBQ8_015 GB19 GB
32 GBQ8_015 GB19 GB
48 GBQ8_015 GB19 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 GBQ2_KRuns well9.8 GB3.1
M6 · 24 GBQ5_K_MRuns well15 GB2.7
M6 · 32 GBQ5_K_MRuns great15 GB2.7
M5 · 16 GBQ2_KRuns well9.8 GB2.8
M5 · 24 GBQ5_K_MRuns well15 GB2.4
M5 · 32 GBQ5_K_MRuns great15 GB2.4
M5 Pro · 24 GBQ5_K_MRuns well15 GB4.8
M5 Pro · 48 GBQ8_0Runs great19 GB5
M5 Pro · 64 GBQ8_0Runs great19 GB5
M5 Max · 36 GBQ6_KRuns great16 GB7
M5 Max · 48 GBQ8_0Runs great19 GB9.9
M5 Max · 64 GBQ8_0Runs great19 GB9.9
M5 Max · 128 GBQ8_0Runs great19 GB9.9
M5 Ultra · 96 GBQ8_0Runs great19 GB19
M5 Ultra · 256 GBQ8_0Runs great19 GB19
M5 Ultra · 512 GBQ8_0Runs great19 GB19
M4 · 16 GBQ2_KRuns well9.8 GB2.2
M4 · 24 GBQ5_K_MRuns well15 GB1.9
M4 · 32 GBQ5_K_MRuns great15 GB1.9
M4 Pro · 24 GBQ5_K_MRuns well15 GB4.2
M4 Pro · 48 GBQ8_0Runs great19 GB4.3
M4 Pro · 64 GBQ8_0Runs great19 GB4.3
M4 Max · 36 GBQ6_KRuns great16 GB6
M4 Max · 48 GBQ8_0Runs great19 GB8.3
M4 Max · 64 GBQ8_0Runs great19 GB8.3
M4 Max · 96 GBQ8_0Runs great19 GB6.4
M4 Max · 128 GBQ8_0Runs great19 GB8.3
M3 · 8 GBQ2_KToo big9.8 GB
M3 · 16 GBQ2_KRuns well9.8 GB1.8
M3 · 24 GBQ5_K_MRuns well15 GB1.6
M3 Pro · 18 GBQ3_K_LRuns well12 GB2.6
M3 Pro · 36 GBQ6_KRuns great16 GB2.3
M3 Max · 36 GBQ6_KRuns great16 GB4.5
M3 Max · 48 GBQ8_0Runs great19 GB6.3
M3 Max · 64 GBQ8_0Runs great19 GB6.3
M3 Max · 96 GBQ8_0Runs great19 GB4.7
M3 Max · 128 GBQ8_0Runs great19 GB6.3
M3 Ultra · 96 GBQ8_0Runs great19 GB12
M3 Ultra · 256 GBQ8_0Runs great19 GB12
M3 Ultra · 512 GBQ8_0Runs great19 GB12
M2 · 8 GBQ2_KToo big9.8 GB
M2 · 16 GBQ2_KRuns well9.8 GB1.8
M2 · 24 GBQ5_K_MRuns well15 GB1.6
M2 Pro · 16 GBQ2_KRuns well9.8 GB3.6
M2 Pro · 32 GBQ5_K_MRuns great15 GB3.1
M2 Max · 32 GBQ5_K_MRuns great15 GB6.1
M2 Max · 64 GBQ8_0Runs great19 GB6.3
M2 Max · 96 GBQ8_0Runs great19 GB6.3
M2 Ultra · 64 GBQ8_0Runs great19 GB12
M2 Ultra · 128 GBQ8_0Runs great19 GB12
M2 Ultra · 192 GBQ8_0Runs great19 GB12
M1 · 8 GBQ2_KToo big9.8 GB
M1 · 16 GBQ2_KRuns well9.8 GB1.2
M1 Pro · 16 GBQ2_KRuns well9.8 GB3.5
M1 Pro · 32 GBQ5_K_MRuns great15 GB3.1
M1 Max · 32 GBQ5_K_MRuns great15 GB5.9
M1 Max · 64 GBQ8_0Runs great19 GB6.1
M1 Ultra · 64 GBQ8_0Runs great19 GB11
M1 Ultra · 128 GBQ8_0Runs great19 GB11

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

Information

Maker
Alibaba Qwen
Released
September 2023
Parameters
14B
Longest chat
8K tokens
Reads pictures
No
Licence
Not stated
Downloads this month
1,119
Likes
1
Sizes
11, 5.8 to 15 GB
Kind
Maker's release

Badge for the model card

Shows on Qwen 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