Outmake Models
Models

Llama 3.1 8B

Meta · July 2024

Get Hugging Face

A 8B chat model from Meta.

Rating
2.3
Downloads
26K
Likes
67
Parameters
8B
Context
128K
Licence
llama3.1

Runs great on M4 · 16 GB

The Q6_K size from unsloth is the one to get: a 6.6 GB download that uses 7.3 GB of memory, and writes about 6.3 words a second.

Ratings

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

Text
1211
Coding
1259

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 8B 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 unsloth/Llama-3.1-8B-Instruct-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.

SizeDownloadMemory at 8KGet
UD-IQ1_S2.2 GB2.9 GBestimatedOpen
UD-IQ1_M2.3 GB3.0 GBestimatedOpen
UD-IQ2_XXS2.5 GB3.2 GBestimatedOpen
UD-IQ2_M3.0 GB3.7 GBestimatedOpen
Q2_K3.2 GB3.9 GBestimatedOpen
Q2_K_L3.3 GB4.0 GBestimatedOpen
UD-IQ3_XXS3.3 GB4.1 GBestimatedOpen
UD-Q2_K_XL3.4 GB4.1 GBestimatedOpen
Q3_K_S3.7 GB4.4 GBestimatedOpen
Q3_K_M4.0 GB4.7 GBestimatedOpen
UD-Q3_K_XL4.2 GB4.9 GBestimatedOpen
IQ4_XS4.5 GB5.2 GBestimatedOpen
Q4_04.7 GB5.4 GBestimatedOpen
IQ4_NL4.7 GB5.4 GBestimatedOpen
Q4_K_S4.7 GB5.4 GBestimatedOpen
Q4_K_M4.9 GB5.6 GBestimatedOpen
UD-Q4_K_XL5.0 GB5.7 GBestimatedOpen
Q4_15.1 GB5.9 GBestimatedOpen
Q5_K_S5.6 GB6.3 GBestimatedOpen
Q5_K_M5.7 GB6.5 GBestimatedOpen
UD-Q5_K_XL5.7 GB6.5 GBestimatedOpen
Q6_K6.6 GB7.3 GBestimatedOpen
UD-Q6_K_XL7.3 GB8.1 GBestimatedOpen
UD-Q8_K_XL11 GB11 GBestimatedOpen
BF1616 GB17 GBestimatedOpen

Run It Anywhere

Llama 3.1 8B is an open model, so any app that runs GGUF files can run it. These take the Q6_K size from unsloth straight from Hugging Face.

  • LM StudioMac, Windows, LinuxOpen
  • JanMac, Windows, LinuxOpen
  • MstyMac, Windows, LinuxOpen
  • OllamaMac, Windows, Linuxollama run hf.co/unsloth/Llama-3.1-8B-Instruct-GGUF:Q6_K
  • llama.cppMac, Windows, Linuxllama-server -hf unsloth/Llama-3.1-8B-Instruct-GGUF:Q6_K
  • Docker Model RunnerMac, Windows, Linuxdocker model run hf.co/unsloth/Llama-3.1-8B-Instruct-GGUF:Q6_K
On a PC Graphics Card
Video memoryLargest size that fitsDownloadMemory at 8K
6 GBQ4_15.1 GB5.9 GB
8 GBQ6_K6.6 GB7.3 GB
10 GBUD-Q6_K_XL7.3 GB8.1 GB
11 GBUD-Q6_K_XL7.3 GB8.1 GB
12 GBUD-Q8_K_XL11 GB11 GB
16 GBUD-Q8_K_XL11 GB11 GB
20 GBBF1616 GB17 GB
24 GBBF1616 GB17 GB
32 GBBF1616 GB17 GB
48 GBBF1616 GB17 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 GBQ6_KRuns great7.3 GB9.2
M6 · 24 GBUD-Q8_K_XLRuns great11 GB6.5
M6 · 32 GBUD-Q8_K_XLRuns great13 GB6.5
M5 · 16 GBQ6_KRuns great7.3 GB8.3
M5 · 24 GBUD-Q8_K_XLRuns great11 GB5.9
M5 · 32 GBUD-Q8_K_XLRuns great13 GB5.9
M5 Pro · 24 GBUD-Q8_K_XLRuns great11 GB12
M5 Pro · 48 GBUD-Q8_K_XLRuns great21 GB12
M5 Pro · 64 GBUD-Q8_K_XLRuns great21 GB12
M5 Max · 36 GBUD-Q8_K_XLRuns great16 GB17
M5 Max · 48 GBUD-Q8_K_XLRuns great21 GB23
M5 Max · 64 GBUD-Q8_K_XLRuns great21 GB23
M5 Max · 128 GBUD-Q8_K_XLRuns great21 GB23
M5 Ultra · 96 GBUD-Q8_K_XLRuns great21 GB44
M5 Ultra · 256 GBUD-Q8_K_XLRuns great21 GB44
M5 Ultra · 512 GBUD-Q8_K_XLRuns great21 GB44
M4 · 16 GBQ6_KRuns great7.3 GB6.3
M4 · 24 GBUD-Q8_K_XLRuns great11 GB4.6
M4 · 32 GBUD-Q8_K_XLRuns great13 GB4.6
M4 Pro · 24 GBUD-Q8_K_XLRuns great11 GB10
M4 Pro · 48 GBUD-Q8_K_XLRuns great21 GB10
M4 Pro · 64 GBUD-Q8_K_XLRuns great21 GB10
M4 Max · 36 GBUD-Q8_K_XLRuns great16 GB15
M4 Max · 48 GBUD-Q8_K_XLRuns great21 GB19
M4 Max · 64 GBUD-Q8_K_XLRuns great21 GB19
M4 Max · 96 GBUD-Q8_K_XLRuns great21 GB15
M4 Max · 128 GBUD-Q8_K_XLRuns great21 GB19
M3 · 8 GBIQ4_XSRuns well5.2 GB6.6
M3 · 16 GBQ6_KRuns great7.3 GB5.3
M3 · 24 GBUD-Q8_K_XLRuns great11 GB3.9
M3 Pro · 18 GBUD-Q6_K_XLRuns great8.7 GB7.4
M3 Pro · 36 GBUD-Q8_K_XLRuns great16 GB5.8
M3 Max · 36 GBUD-Q8_K_XLRuns great16 GB11
M3 Max · 48 GBUD-Q8_K_XLRuns great21 GB15
M3 Max · 64 GBUD-Q8_K_XLRuns great21 GB15
M3 Max · 96 GBUD-Q8_K_XLRuns great21 GB11
M3 Max · 128 GBUD-Q8_K_XLRuns great21 GB15
M3 Ultra · 96 GBUD-Q8_K_XLRuns great21 GB27
M3 Ultra · 256 GBUD-Q8_K_XLRuns great21 GB27
M3 Ultra · 512 GBUD-Q8_K_XLRuns great21 GB27
M2 · 8 GBIQ4_XSRuns well5.2 GB6.6
M2 · 16 GBQ6_KRuns great7.3 GB5.3
M2 · 24 GBUD-Q8_K_XLRuns great11 GB3.9
M2 Pro · 16 GBQ6_KRuns great7.3 GB10
M2 Pro · 32 GBUD-Q8_K_XLRuns great13 GB7.6
M2 Max · 32 GBUD-Q8_K_XLRuns great13 GB15
M2 Max · 64 GBUD-Q8_K_XLRuns great21 GB15
M2 Max · 96 GBUD-Q8_K_XLRuns great21 GB15
M2 Ultra · 64 GBUD-Q8_K_XLRuns great21 GB27
M2 Ultra · 128 GBUD-Q8_K_XLRuns great21 GB27
M2 Ultra · 192 GBUD-Q8_K_XLRuns great21 GB27
M1 · 8 GBIQ4_XSRuns well5.2 GB4.4
M1 · 16 GBQ6_KRuns great7.3 GB3.6
M1 Pro · 16 GBQ6_KRuns great7.3 GB9.9
M1 Pro · 32 GBUD-Q8_K_XLRuns great13 GB7.4
M1 Max · 32 GBUD-Q8_K_XLRuns great13 GB14
M1 Max · 64 GBUD-Q8_K_XLRuns great21 GB14
M1 Ultra · 64 GBUD-Q8_K_XLRuns great21 GB24
M1 Ultra · 128 GBUD-Q8_K_XLRuns great21 GB24

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
Meta
Released
July 2024
Parameters
8B
Longest chat
128K tokens
Reads pictures
No
Licence
llama3.1
Downloads this month
25,774
Likes
67
Sizes
25, 2.2 to 16 GB
Kind
Maker's release

Badge for the model card

Shows on Llama 3.1 8B'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