Outmake Models
Models

Llama 3 1 Nemotron 51B

NVIDIA · September 2024

Get Hugging Face

A 52B chat model from NVIDIA.

Rating
2.9
Downloads
3.1K
Likes
5
Parameters
52B
Context
128K
Licence
other

Too big for this Mac

Its smallest size needs 29 GB of memory, more than M4 · 16 GB can give it.

Ratings

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

Text
1287
Coding
1312

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.

Llama 3 1 Nemotron 51B runs well from a Mac with an M2 and 24 GB of memory. 47 of 59 Mac configurations run it well.

Compare with

The nearest models in size.

Sizes

From bartowski/Llama-3_1-Nemotron-51B-Instruct-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.

SizeDownloadMemory at 8KGet
IQ2_XXS14 GB15 GBestimatedOpen
IQ2_XS16 GB17 GBestimatedOpen
IQ2_S16 GB17 GBestimatedOpen
IQ2_M18 GB19 GBestimatedOpen
Q2_K19 GB20 GBestimatedOpen
Q2_K_L20 GB21 GBestimatedOpen
IQ3_XS22 GB23 GBestimatedOpen
Q3_K_S23 GB24 GBestimatedOpen
IQ3_M23 GB24 GBestimatedOpen
Q3_K_M25 GB26 GBestimatedOpen
Q3_K_L27 GB28 GBestimatedOpen
IQ4_XS28 GB29 GBestimatedOpen
Q3_K_XL28 GB29 GBestimatedOpen
IQ4_NL29 GB30 GBestimatedOpen
Q4_029 GB30 GBestimatedOpen
Q4_K_S29 GB30 GBestimatedOpen
Q4_K_M31 GB32 GBestimatedOpen
Q4_K_L32 GB33 GBestimatedOpen
Q4_132 GB33 GBestimatedOpen
Q5_K_S36 GB37 GBestimatedOpen
Q5_K_M36 GB37 GBestimatedOpen
Q5_K_L37 GB38 GBestimatedOpen
Q6_K42 GB43 GBestimatedOpen
Q6_K_L43 GB44 GBestimatedOpen
Q8_055 GB56 GBestimatedOpen
F16103 GB104 GBestimatedOpen

Run It Anywhere

Llama 3 1 Nemotron 51B 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/Llama-3_1-Nemotron-51B-Instruct-GGUF:IQ2_XXS
  • llama.cppMac, Windows, Linuxllama-server -hf bartowski/Llama-3_1-Nemotron-51B-Instruct-GGUF:IQ2_XXS
  • Docker Model RunnerMac, Windows, Linuxdocker model run hf.co/bartowski/Llama-3_1-Nemotron-51B-Instruct-GGUF:IQ2_XXS
On a PC Graphics Card
Video memoryLargest size that fitsDownloadMemory at 8K
6 GBNone worth runningneeds 23 GB
8 GBNone worth runningneeds 23 GB
10 GBNone worth runningneeds 23 GB
11 GBNone worth runningneeds 23 GB
12 GBNone worth runningneeds 23 GB
16 GBNone worth runningneeds 23 GB
20 GBNone worth runningneeds 23 GB
24 GBQ3_K_S23 GB24 GB
32 GBQ4_K_S29 GB30 GB
48 GBQ6_K_L43 GB44 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_XXSToo big29 GB
M6 · 24 GBIQ2_XXSRuns well16 GB4.7
M6 · 32 GBQ2_KRuns well20 GB3.7
M5 · 16 GBIQ2_XXSToo big29 GB
M5 · 24 GBIQ2_XXSRuns well16 GB4.3
M5 · 32 GBQ2_KRuns well20 GB3.4
M5 Pro · 24 GBIQ2_XXSRuns well16 GB8.4
M5 Pro · 48 GBQ4_K_SRuns well31 GB4.8
M5 Pro · 64 GBQ4_K_SRuns great30 GB4.8
M5 Max · 36 GBQ3_K_SRuns well24 GB8.8
M5 Max · 48 GBQ4_K_SRuns well31 GB9.4
M5 Max · 64 GBQ4_K_SRuns great30 GB9.4
M5 Max · 128 GBQ8_0Runs great62 GB6.7
M5 Ultra · 96 GBQ6_K_LRuns great45 GB14
M5 Ultra · 256 GBQ8_0Runs great69 GB13
M5 Ultra · 512 GBQ8_0Runs great69 GB13
M4 · 16 GBIQ2_XXSToo big29 GB
M4 · 24 GBIQ2_XXSRuns well16 GB3.3
M4 · 32 GBQ2_KRuns well20 GB2.7
M4 Pro · 24 GBIQ2_XXSRuns well16 GB7
M4 Pro · 48 GBQ4_K_SRuns well31 GB4.2
M4 Pro · 64 GBQ4_K_SRuns great30 GB4.2
M4 Max · 36 GBQ3_K_SRuns well24 GB7.3
M4 Max · 48 GBQ4_K_SRuns well31 GB7.8
M4 Max · 64 GBQ4_K_SRuns great30 GB7.8
M4 Max · 96 GBQ6_K_LRuns great45 GB4.6
M4 Max · 128 GBQ8_0Runs great62 GB5.5
M3 · 8 GBIQ2_XXSToo big29 GB
M3 · 16 GBIQ2_XXSToo big29 GB
M3 · 24 GBIQ2_XXSRuns well16 GB2.8
M3 Pro · 18 GBIQ2_XXSToo big29 GB
M3 Pro · 36 GBQ3_K_SRuns well24 GB2.9
M3 Max · 36 GBQ3_K_SRuns well24 GB5.6
M3 Max · 48 GBQ4_K_SRuns well31 GB6
M3 Max · 64 GBQ4_K_SRuns great30 GB6
M3 Max · 96 GBQ6_K_LRuns great45 GB3.5
M3 Max · 128 GBQ8_0Runs great62 GB4.2
M3 Ultra · 96 GBQ6_K_LRuns great45 GB8.4
M3 Ultra · 256 GBQ8_0Runs great69 GB7.9
M3 Ultra · 512 GBQ8_0Runs great69 GB7.9
M2 · 8 GBIQ2_XXSToo big29 GB
M2 · 16 GBIQ2_XXSToo big29 GB
M2 · 24 GBIQ2_XXSRuns well16 GB2.8
M2 Pro · 16 GBIQ2_XXSToo big29 GB
M2 Pro · 32 GBQ2_KRuns well20 GB4.3
M2 Max · 32 GBQ2_KRuns well20 GB8.1
M2 Max · 64 GBQ4_K_SRuns great30 GB6
M2 Max · 96 GBQ6_K_LRuns great45 GB4.5
M2 Ultra · 64 GBQ4_K_SRuns great30 GB11
M2 Ultra · 128 GBQ8_0Runs great62 GB7.9
M2 Ultra · 192 GBQ8_0Runs great69 GB7.9
M1 · 8 GBIQ2_XXSToo big29 GB
M1 · 16 GBIQ2_XXSToo big29 GB
M1 Pro · 16 GBIQ2_XXSToo big29 GB
M1 Pro · 32 GBQ2_KRuns well20 GB4.1
M1 Max · 32 GBQ2_KRuns well20 GB7.4
M1 Max · 64 GBQ4_K_SRuns great30 GB5.7
M1 Ultra · 64 GBQ4_K_SRuns great30 GB9.8
M1 Ultra · 128 GBQ8_0Runs great62 GB7.3

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

Information

Maker
NVIDIA
Released
September 2024
Parameters
52B
Longest chat
128K tokens
Reads pictures
No
Licence
other
Downloads this month
3,115
Likes
5
Sizes
26, 14 to 103 GB
Kind
Maker's release

Badge for the model card

Shows on Llama 3 1 Nemotron 51B'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