Outmake Models
Models

Granite 4.2 30B

IBM · August 2026

Get Hugging Face

A 29B chat model from IBM.

Rating
3.4
Downloads
249K
Likes
39
Parameters
29B
Context
128K
Licence
apache-2.0

Runs well on M4 · 16 GB

The IQ2_XXS size from bartowski is the one to get: a 9.0 GB download that uses 10 GB of memory, and writes about 3.9 words a second.

Ratings

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

Text
1340
Coding
1399

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.

Granite 4.2 30B 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 ibm-granite/granite-4.2-30b-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.

SizeDownloadMemory at 8KGet
Q2_K11 GB12 GBestimatedOpen
Q3_K_S13 GB14 GBestimatedOpen
Q3_K_M14 GB15 GBestimatedOpen
Q3_K_L15 GB17 GBestimatedOpen
Q4_017 GB18 GBestimatedOpen
Q4_K_S17 GB18 GBestimatedOpen
Q4_K_M18 GB19 GBestimatedOpen
Q4_118 GB20 GBestimatedOpen
Q5_020 GB22 GBestimatedOpen
Q5_K_S20 GB22 GBestimatedOpen
Q5_K_M21 GB22 GBestimatedOpen
Q5_122 GB23 GBestimatedOpen
Q6_K24 GB25 GBestimatedOpen
Q8_031 GB32 GBestimatedOpen
BF1659 GB60 GBestimatedOpen

Run It Anywhere

Granite 4.2 30B is an open model, so any app that runs GGUF files can run it. These take the IQ2_XXS size from bartowski straight from Hugging Face.

  • LM StudioMac, Windows, LinuxOpen
  • JanMac, Windows, LinuxOpen
  • MstyMac, Windows, LinuxOpen
  • OllamaMac, Windows, Linuxollama run hf.co/bartowski/granite-4.2-30b-GGUF:IQ2_XXS
  • llama.cppMac, Windows, Linuxllama-server -hf bartowski/granite-4.2-30b-GGUF:IQ2_XXS
  • Docker Model RunnerMac, Windows, Linuxdocker model run hf.co/bartowski/granite-4.2-30b-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 GBQ3_K_M14 GB15 GB
20 GBQ4_118 GB20 GB
24 GBQ5_122 GB23 GB
32 GBQ6_K24 GB25 GB
48 GBQ8_031 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 GBIQ2_XXSRuns well10 GB5.5
M6 · 24 GBQ3_K_MRuns well15 GB4.3
M6 · 32 GBQ4_1Runs well21 GB4.1
M5 · 16 GBIQ2_XXSRuns well10 GB5
M5 · 24 GBQ3_K_MRuns well15 GB3.9
M5 · 32 GBQ4_1Runs well21 GB3.7
M5 Pro · 24 GBQ3_K_MRuns well15 GB7.6
M5 Pro · 48 GBQ5_K_MRuns great22 GB5.9
M5 Pro · 64 GBQ6_KRuns great29 GB5.6
M5 Max · 36 GBQ3_K_LRuns great17 GB11
M5 Max · 48 GBQ5_K_MRuns great22 GB12
M5 Max · 64 GBQ6_KRuns great29 GB11
M5 Max · 128 GBQ8_0Runs great51 GB10
M5 Ultra · 96 GBQ8_0Runs great41 GB20
M5 Ultra · 256 GBQ8_0Runs great51 GB20
M5 Ultra · 512 GBQ8_0Runs great51 GB20
M4 · 16 GBIQ2_XXSRuns well10 GB3.9
M4 · 24 GBQ3_K_MRuns well15 GB3
M4 · 32 GBQ4_1Runs well21 GB2.9
M4 Pro · 24 GBQ3_K_MRuns well15 GB6.5
M4 Pro · 48 GBQ5_K_MRuns great22 GB5.1
M4 Pro · 64 GBQ6_KRuns great29 GB4.7
M4 Max · 36 GBQ3_K_LRuns great17 GB8.9
M4 Max · 48 GBQ5_K_MRuns great22 GB9.5
M4 Max · 64 GBQ6_KRuns great29 GB8.7
M4 Max · 96 GBQ8_0Runs great41 GB6.4
M4 Max · 128 GBQ8_0Runs great51 GB8.3
M3 · 8 GBIQ2_XXSToo big29 GB
M3 · 16 GBIQ2_XXSRuns well10 GB3.3
M3 · 24 GBQ3_K_MRuns well15 GB2.5
M3 Pro · 18 GBIQ2_SRuns well11 GB4.5
M3 Pro · 36 GBQ3_K_LRuns great17 GB3.6
M3 Max · 36 GBQ3_K_LRuns great17 GB6.9
M3 Max · 48 GBQ5_K_MRuns great22 GB7.4
M3 Max · 64 GBQ6_KRuns great29 GB6.7
M3 Max · 96 GBQ8_0Runs great41 GB4.9
M3 Max · 128 GBQ8_0Runs great51 GB6.4
M3 Ultra · 96 GBQ8_0Runs great41 GB12
M3 Ultra · 256 GBQ8_0Runs great51 GB12
M3 Ultra · 512 GBQ8_0Runs great51 GB12
M2 · 8 GBIQ2_XXSToo big29 GB
M2 · 16 GBIQ2_XXSRuns well10 GB3.3
M2 · 24 GBQ3_K_MRuns well15 GB2.5
M2 Pro · 16 GBIQ2_XXSRuns well10 GB6.3
M2 Pro · 32 GBQ4_1Runs well21 GB4.8
M2 Max · 32 GBQ4_1Runs well21 GB9
M2 Max · 64 GBQ6_KRuns great29 GB6.7
M2 Max · 96 GBQ8_0Runs great41 GB6.3
M2 Ultra · 64 GBQ6_KRuns great29 GB12
M2 Ultra · 128 GBQ8_0Runs great51 GB12
M2 Ultra · 192 GBQ8_0Runs great51 GB12
M1 · 8 GBIQ2_XXSToo big29 GB
M1 · 16 GBIQ2_XXSRuns well10 GB2.2
M1 Pro · 16 GBIQ2_XXSRuns well10 GB5.9
M1 Pro · 32 GBQ4_1Runs well21 GB4.6
M1 Max · 32 GBQ4_1Runs well21 GB8.5
M1 Max · 64 GBQ6_KRuns great29 GB6.3
M1 Ultra · 64 GBQ6_KRuns great29 GB11
M1 Ultra · 128 GBQ8_0Runs great51 GB11

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

Packaged by

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

Information

Maker
IBM
Released
August 2026
Parameters
29B
Longest chat
128K tokens
Reads pictures
No
Licence
apache-2.0
Downloads this month
249,323
Likes
39
Sizes
15, 11 to 59 GB
Kind
Maker's release

Badge for the model card

Shows on Granite 4.2 30B'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