Outmake Models
Models

Nl2sh 1.5B Q4 K M

ThorOdinson246 · August 2026

Get Hugging Face

A 1.5B chat model from ThorOdinson246.

Downloads
100K
Likes
65
Parameters
1.5B
Context
32K
Licence
apache-2.0

Runs great on M4 · 16 GB

The Q4_K_M size from ThorOdinson246 is the one to get: a 1.0 GB download that uses 1.6 GB of memory, and writes about 30 words a second.

Nl2sh 1.5B Q4 K M 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 ThorOdinson246/nl2sh-1.5b-Q4_K_M on Hugging Face. A smaller size is a smaller download and a little less accurate.

SizeDownloadMemory at 8KGet
Q4_K_M1.0 GB1.2 GBestimatedOpen

Run It Anywhere

Nl2sh 1.5B Q4 K M is an open model, so any app that runs GGUF files can run it. These take the Q4_K_M size from ThorOdinson246 straight from Hugging Face.

  • LM StudioMac, Windows, LinuxOpen
  • JanMac, Windows, LinuxOpen
  • MstyMac, Windows, LinuxOpen
  • OllamaMac, Windows, Linuxollama run hf.co/ThorOdinson246/nl2sh-1.5b-Q4_K_M:Q4_K_M
  • llama.cppMac, Windows, Linuxllama-server -hf ThorOdinson246/nl2sh-1.5b-Q4_K_M:Q4_K_M
  • Docker Model RunnerMac, Windows, Linuxdocker model run hf.co/ThorOdinson246/nl2sh-1.5b-Q4_K_M:Q4_K_M
On a PC Graphics Card
Video memoryLargest size that fitsDownloadMemory at 8K
6 GBQ4_K_M1.0 GB1.2 GB
8 GBQ4_K_M1.0 GB1.2 GB
10 GBQ4_K_M1.0 GB1.2 GB
11 GBQ4_K_M1.0 GB1.2 GB
12 GBQ4_K_M1.0 GB1.2 GB
16 GBQ4_K_M1.0 GB1.2 GB
20 GBQ4_K_M1.0 GB1.2 GB
24 GBQ4_K_M1.0 GB1.2 GB
32 GBQ4_K_M1.0 GB1.2 GB
48 GBQ4_K_M1.0 GB1.2 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_K_MRuns great1.6 GB46
M6 · 24 GBQ4_K_MRuns great1.6 GB46
M6 · 32 GBQ4_K_MRuns great1.6 GB46
M5 · 16 GBQ4_K_MRuns great1.6 GB43
M5 · 24 GBQ4_K_MRuns great1.6 GB43
M5 · 32 GBQ4_K_MRuns great1.6 GB43
M5 Pro · 24 GBQ4_K_MRuns great1.6 GB81
M5 Pro · 48 GBQ4_K_MRuns great1.6 GB81
M5 Pro · 64 GBQ4_K_MRuns great1.6 GB81
M5 Max · 36 GBQ4_K_MRuns great1.6 GB113
M5 Max · 48 GBQ4_K_MRuns great1.6 GB142
M5 Max · 64 GBQ4_K_MRuns great1.6 GB142
M5 Max · 128 GBQ4_K_MRuns great1.6 GB142
M5 Ultra · 96 GBQ4_K_MRuns great1.6 GB229
M5 Ultra · 256 GBQ4_K_MRuns great1.6 GB229
M5 Ultra · 512 GBQ4_K_MRuns great1.6 GB229
M4 · 16 GBQ4_K_MRuns great1.6 GB30
M4 · 24 GBQ4_K_MRuns great1.6 GB30
M4 · 32 GBQ4_K_MRuns great1.6 GB30
M4 Pro · 24 GBQ4_K_MRuns great1.6 GB54
M4 Pro · 48 GBQ4_K_MRuns great1.6 GB54
M4 Pro · 64 GBQ4_K_MRuns great1.6 GB54
M4 Max · 36 GBQ4_K_MRuns great1.6 GB69
M4 Max · 48 GBQ4_K_MRuns great1.6 GB80
M4 Max · 64 GBQ4_K_MRuns great1.6 GB80
M4 Max · 96 GBQ4_K_MRuns great1.6 GB69
M4 Max · 128 GBQ4_K_MRuns great1.6 GB80
M3 · 8 GBQ4_K_MRuns great1.6 GB27
M3 · 16 GBQ4_K_MRuns great1.6 GB27
M3 · 24 GBQ4_K_MRuns great1.6 GB27
M3 Pro · 18 GBQ4_K_MRuns great1.6 GB37
M3 Pro · 36 GBQ4_K_MRuns great1.6 GB37
M3 Max · 36 GBQ4_K_MRuns great1.6 GB61
M3 Max · 48 GBQ4_K_MRuns great1.6 GB73
M3 Max · 64 GBQ4_K_MRuns great1.6 GB73
M3 Max · 96 GBQ4_K_MRuns great1.6 GB61
M3 Max · 128 GBQ4_K_MRuns great1.6 GB73
M3 Ultra · 96 GBQ4_K_MRuns great1.6 GB104
M3 Ultra · 256 GBQ4_K_MRuns great1.6 GB104
M3 Ultra · 512 GBQ4_K_MRuns great1.6 GB104
M2 · 8 GBQ4_K_MRuns great1.6 GB26
M2 · 16 GBQ4_K_MRuns great1.6 GB26
M2 · 24 GBQ4_K_MRuns great1.6 GB26
M2 Pro · 16 GBQ4_K_MRuns great1.6 GB46
M2 Pro · 32 GBQ4_K_MRuns great1.6 GB46
M2 Max · 32 GBQ4_K_MRuns great1.6 GB73
M2 Max · 64 GBQ4_K_MRuns great1.6 GB73
M2 Max · 96 GBQ4_K_MRuns great1.6 GB73
M2 Ultra · 64 GBQ4_K_MRuns great1.6 GB103
M2 Ultra · 128 GBQ4_K_MRuns great1.6 GB103
M2 Ultra · 192 GBQ4_K_MRuns great1.6 GB103
M1 · 8 GBQ4_K_MRuns great1.6 GB18
M1 · 16 GBQ4_K_MRuns great1.6 GB18
M1 Pro · 16 GBQ4_K_MRuns great1.6 GB39
M1 Pro · 32 GBQ4_K_MRuns great1.6 GB39
M1 Max · 32 GBQ4_K_MRuns great1.6 GB57
M1 Max · 64 GBQ4_K_MRuns great1.6 GB57
M1 Ultra · 64 GBQ4_K_MRuns great1.6 GB74
M1 Ultra · 128 GBQ4_K_MRuns great1.6 GB74

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

Information

Maker
ThorOdinson246
Released
August 2026
Parameters
1.5B
Longest chat
32K tokens
Reads pictures
No
Licence
apache-2.0
Downloads this month
99,759
Likes
65
Sizes
1, 1.0 to 1.0 GB
Kind
Maker's release

Badge for the model card

Shows on Nl2sh 1.5B Q4 K M'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