Outmake Models
Models

Dirk Qwen3.8 27B

peculiar-ragdoll · August 2026

Get Hugging Face

A 27B chat model from peculiar-ragdoll that reads pictures as well as text.

Downloads
1.4M
Likes
258
Parameters
27B
Context
256K
Licence
apache-2.0

Runs well on M4 · 16 GB

The UD-Q2_K_XL size from peculiar-ragdoll is the one to get: a 9.8 GB download that uses 11 GB of memory, and writes about 5.4 words a second.

Dirk Qwen3.8 27B 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 peculiar-ragdoll/Dirk-Qwen3.8-27B-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.

SizeDownloadMemory at 8KGet
IQ2_XS8.8 GB9.2 GBestimatedOpen
IQ2_S9.6 GB10 GBestimatedOpen
UD-Q2_K_XL9.8 GB10 GBestimatedOpen
IQ3_XXS10 GB11 GBestimatedOpen
IQ3_S12 GB13 GBestimatedOpen
UD-Q3_K_XL13 GB14 GBestimatedOpen
UD-IQ4_XS14 GB15 GBestimatedOpen
UD-Q4_K_S15 GB16 GBestimatedOpen
UD-Q4_K_M16 GB17 GBestimatedOpen
UD-Q4_K_XL18 GB18 GBestimatedOpen
UD-Q5_K_XL21 GB21 GBestimatedOpen
UD-Q6_K22 GB22 GBestimatedOpen
UD-Q6_K_XL25 GB26 GBestimatedOpen
UD-Q8_K_L28 GB28 GBestimatedOpen
UD-Q8_K_XL31 GB32 GBestimatedOpen

Run It Anywhere

Dirk Qwen3.8 27B is an open model, so any app that runs GGUF files can run it. These take the UD-Q2_K_XL size from peculiar-ragdoll straight from Hugging Face.

  • LM StudioMac, Windows, LinuxOpen
  • JanMac, Windows, LinuxOpen
  • MstyMac, Windows, LinuxOpen
  • OllamaMac, Windows, Linuxollama run hf.co/peculiar-ragdoll/Dirk-Qwen3.8-27B-GGUF:UD-Q2_K_XL
  • llama.cppMac, Windows, Linuxllama-server -hf peculiar-ragdoll/Dirk-Qwen3.8-27B-GGUF:UD-Q2_K_XL
  • Docker Model RunnerMac, Windows, Linuxdocker model run hf.co/peculiar-ragdoll/Dirk-Qwen3.8-27B-GGUF:UD-Q2_K_XL
On a PC Graphics Card
Video memoryLargest size that fitsDownloadMemory at 8K
6 GBNone worth runningneeds 10 GB
8 GBNone worth runningneeds 10 GB
10 GBNone worth runningneeds 10 GB
11 GBUD-Q2_K_XL9.8 GB10 GB
12 GBIQ3_XXS10 GB11 GB
16 GBUD-Q4_K_S15 GB16 GB
20 GBUD-Q4_K_XL18 GB18 GB
24 GBUD-Q6_K22 GB22 GB
32 GBUD-Q8_K_L28 GB28 GB
48 GBUD-Q8_K_XL31 GB32 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-Q2_K_XLRuns well11 GB7.7
M6 · 24 GBUD-Q4_K_SRuns well16 GB5.3
M6 · 32 GBUD-IQ4_XSRuns great15 GB5.7
M5 · 16 GBUD-Q2_K_XLRuns well11 GB7.1
M5 · 24 GBUD-Q4_K_SRuns well16 GB4.9
M5 · 32 GBUD-IQ4_XSRuns great15 GB5.2
M5 Pro · 24 GBUD-Q4_K_SRuns well16 GB9.6
M5 Pro · 48 GBUD-Q6_KRuns great23 GB7
M5 Pro · 64 GBUD-Q8_K_LRuns great31 GB5.6
M5 Max · 36 GBUD-Q4_K_MRuns great17 GB13
M5 Max · 48 GBUD-Q6_KRuns great23 GB14
M5 Max · 64 GBUD-Q8_K_LRuns great31 GB11
M5 Max · 128 GBUD-Q8_K_XLRuns great42 GB10
M5 Ultra · 96 GBUD-Q8_K_XLRuns great42 GB19
M5 Ultra · 256 GBUD-Q8_K_XLRuns great42 GB19
M5 Ultra · 512 GBUD-Q8_K_XLRuns great42 GB19
M4 · 16 GBUD-Q2_K_XLRuns well11 GB5.4
M4 · 24 GBUD-Q4_K_SRuns well16 GB3.8
M4 · 32 GBUD-IQ4_XSRuns great15 GB4.1
M4 Pro · 24 GBUD-Q4_K_SRuns well16 GB8.1
M4 Pro · 48 GBUD-Q6_KRuns great23 GB6.1
M4 Pro · 64 GBUD-Q8_K_LRuns great31 GB4.9
M4 Max · 36 GBUD-Q4_K_MRuns great17 GB11
M4 Max · 48 GBUD-Q6_KRuns great23 GB11
M4 Max · 64 GBUD-Q8_K_LRuns great31 GB9.2
M4 Max · 96 GBUD-Q8_K_XLRuns great42 GB6.5
M4 Max · 128 GBUD-Q8_K_XLRuns great42 GB8.4
M3 · 8 GBIQ2_XSToo big19 GB
M3 · 16 GBUD-Q2_K_XLRuns well11 GB4.6
M3 · 24 GBUD-Q4_K_SRuns well16 GB3.2
M3 Pro · 18 GBIQ3_XXSRuns well12 GB6.4
M3 Pro · 36 GBUD-Q4_K_MRuns great17 GB4.5
M3 Max · 36 GBUD-Q4_K_MRuns great17 GB8.5
M3 Max · 48 GBUD-Q6_KRuns great23 GB8.7
M3 Max · 64 GBUD-Q8_K_LRuns great31 GB7.1
M3 Max · 96 GBUD-Q8_K_XLRuns great42 GB4.9
M3 Max · 128 GBUD-Q8_K_XLRuns great42 GB6.5
M3 Ultra · 96 GBUD-Q8_K_XLRuns great42 GB12
M3 Ultra · 256 GBUD-Q8_K_XLRuns great42 GB12
M3 Ultra · 512 GBUD-Q8_K_XLRuns great42 GB12
M2 · 8 GBIQ2_XSToo big19 GB
M2 · 16 GBUD-Q2_K_XLRuns well11 GB4.6
M2 · 24 GBUD-Q4_K_SRuns well16 GB3.2
M2 Pro · 16 GBUD-Q2_K_XLRuns well11 GB8.7
M2 Pro · 32 GBUD-IQ4_XSRuns great15 GB6.6
M2 Max · 32 GBUD-IQ4_XSRuns great15 GB12
M2 Max · 64 GBUD-Q8_K_LRuns great31 GB7.1
M2 Max · 96 GBUD-Q8_K_XLRuns great42 GB6.4
M2 Ultra · 64 GBUD-Q8_K_LRuns great31 GB13
M2 Ultra · 128 GBUD-Q8_K_XLRuns great42 GB12
M2 Ultra · 192 GBUD-Q8_K_XLRuns great42 GB12
M1 · 8 GBIQ2_XSToo big19 GB
M1 · 16 GBUD-Q2_K_XLRuns well11 GB3.1
M1 Pro · 16 GBUD-Q2_K_XLRuns well11 GB8.1
M1 Pro · 32 GBUD-IQ4_XSRuns great15 GB6.2
M1 Max · 32 GBUD-IQ4_XSRuns great15 GB11
M1 Max · 64 GBUD-Q8_K_LRuns great31 GB6.7
M1 Ultra · 64 GBUD-Q8_K_LRuns great31 GB12
M1 Ultra · 128 GBUD-Q8_K_XLRuns great42 GB11

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

Information

Maker
peculiar-ragdoll
Released
August 2026
Parameters
27B
Longest chat
256K tokens
Reads pictures
Yes
Licence
apache-2.0
Downloads this month
1,372,229
Likes
258
Sizes
15, 8.8 to 31 GB
Kind
Maker's release

Badge for the model card

Shows on Dirk Qwen3.8 27B'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