Outmake Models
Models

Aya Expanse 8B

Cohere · October 2024

Get Hugging Face

A 8B chat model from Cohere.

Rating
2.3
Downloads
6.6K
Likes
47
Parameters
8B
Context
8K
Licence
cc-by-nc-4.0

Runs great on M4 · 16 GB

The Q6_K_L size from bartowski is the one to get: a 6.9 GB download that uses 7.6 GB of memory, and writes about 6.2 words a second.

Ratings

2.3 out of 5, across people's blind votes on its answers and the tests below.

Text
1223
Coding
1255

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.

KnowledgeMMLU-Pro
33.7%

MMLU-Pro: graduate-level questions in 14 subjects. Scores are the ones filed on the model's Hugging Face page or the board's own table, read 2026-11-05; some come from the maker.

Aya Expanse 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 bartowski/aya-expanse-8b-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.

SizeDownloadMemory at 8KGet
IQ2_M3.1 GB3.8 GBestimatedOpen
Q2_K3.4 GB4.2 GBestimatedOpen
Q2_K_L3.7 GB4.4 GBestimatedOpen
IQ3_XS3.7 GB4.5 GBestimatedOpen
Q3_K_S3.9 GB4.6 GBestimatedOpen
IQ3_M4.0 GB4.7 GBestimatedOpen
Q3_K_M4.2 GB5.0 GBestimatedOpen
Q3_K_L4.5 GB5.3 GBestimatedOpen
IQ4_XS4.6 GB5.3 GBestimatedOpen
Q3_K_XL4.8 GB5.5 GBestimatedOpen
Q4_0_4_44.8 GB5.5 GBestimatedOpen
Q4_0_4_84.8 GB5.5 GBestimatedOpen
Q4_0_8_84.8 GB5.5 GBestimatedOpen
Q4_04.8 GB5.5 GBestimatedOpen
Q4_K_S4.8 GB5.6 GBestimatedOpen
Q4_K_M5.1 GB5.8 GBestimatedOpen
Q4_K_L5.3 GB6.0 GBestimatedOpen
Q5_K_S5.7 GB6.4 GBestimatedOpen
Q5_K_M5.8 GB6.5 GBestimatedOpen
Q5_K_L6.1 GB6.8 GBestimatedOpen
Q6_K6.6 GB7.3 GBestimatedOpen
Q6_K_L6.9 GB7.6 GBestimatedOpen
Q8_08.5 GB9.3 GBestimatedOpen
F1616 GB17 GBestimatedOpen

Run It Anywhere

Aya Expanse 8B is an open model, so any app that runs GGUF files can run it. These take the Q6_K_L size from bartowski straight from Hugging Face.

  • LM StudioMac, Windows, LinuxOpen
  • JanMac, Windows, LinuxOpen
  • MstyMac, Windows, LinuxOpen
  • OllamaMac, Windows, Linuxollama run hf.co/bartowski/aya-expanse-8b-GGUF:Q6_K_L
  • llama.cppMac, Windows, Linuxllama-server -hf bartowski/aya-expanse-8b-GGUF:Q6_K_L
  • Docker Model RunnerMac, Windows, Linuxdocker model run hf.co/bartowski/aya-expanse-8b-GGUF:Q6_K_L
On a PC Graphics Card
Video memoryLargest size that fitsDownloadMemory at 8K
6 GBQ4_K_M5.1 GB5.8 GB
8 GBQ6_K_L6.9 GB7.6 GB
10 GBQ8_08.5 GB9.3 GB
11 GBQ8_08.5 GB9.3 GB
12 GBQ8_08.5 GB9.3 GB
16 GBQ8_08.5 GB9.3 GB
20 GBF1616 GB17 GB
24 GBF1616 GB17 GB
32 GBF1616 GB17 GB
48 GBF1616 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_K_LRuns great7.6 GB9
M6 · 24 GBQ8_0Runs great9.3 GB8.9
M6 · 32 GBQ8_0Runs great9.3 GB8.9
M5 · 16 GBQ6_K_LRuns great7.6 GB8.2
M5 · 24 GBQ8_0Runs great9.3 GB8.1
M5 · 32 GBQ8_0Runs great9.3 GB8.1
M5 Pro · 24 GBQ8_0Runs great9.3 GB16
M5 Pro · 48 GBQ8_0Runs great9.3 GB16
M5 Pro · 64 GBQ8_0Runs great9.3 GB16
M5 Max · 36 GBQ8_0Runs great9.3 GB24
M5 Max · 48 GBQ8_0Runs great9.3 GB31
M5 Max · 64 GBQ8_0Runs great9.3 GB31
M5 Max · 128 GBQ8_0Runs great9.3 GB31
M5 Ultra · 96 GBQ8_0Runs great9.3 GB59
M5 Ultra · 256 GBQ8_0Runs great9.3 GB59
M5 Ultra · 512 GBQ8_0Runs great9.3 GB59
M4 · 16 GBQ6_K_LRuns great7.6 GB6.2
M4 · 24 GBQ8_0Runs great9.3 GB6.1
M4 · 32 GBQ8_0Runs great9.3 GB6.1
M4 Pro · 24 GBQ8_0Runs great9.3 GB13
M4 Pro · 48 GBQ8_0Runs great9.3 GB13
M4 Pro · 64 GBQ8_0Runs great9.3 GB13
M4 Max · 36 GBQ8_0Runs great9.3 GB19
M4 Max · 48 GBQ8_0Runs great9.3 GB24
M4 Max · 64 GBQ8_0Runs great9.3 GB24
M4 Max · 96 GBQ8_0Runs great9.3 GB19
M4 Max · 128 GBQ8_0Runs great9.3 GB24
M3 · 8 GBQ3_K_LRuns well5.3 GB6.5
M3 · 16 GBQ6_K_LRuns great7.6 GB5.2
M3 · 24 GBQ8_0Runs great9.3 GB5.2
M3 Pro · 18 GBQ6_K_LRuns great7.6 GB7.7
M3 Pro · 36 GBQ8_0Runs great9.3 GB7.6
M3 Max · 36 GBQ8_0Runs great9.3 GB15
M3 Max · 48 GBQ8_0Runs great9.3 GB19
M3 Max · 64 GBQ8_0Runs great9.3 GB19
M3 Max · 96 GBQ8_0Runs great9.3 GB15
M3 Max · 128 GBQ8_0Runs great9.3 GB19
M3 Ultra · 96 GBQ8_0Runs great9.3 GB34
M3 Ultra · 256 GBQ8_0Runs great9.3 GB34
M3 Ultra · 512 GBQ8_0Runs great9.3 GB34
M2 · 8 GBQ3_K_LRuns well5.3 GB6.5
M2 · 16 GBQ6_K_LRuns great7.6 GB5.2
M2 · 24 GBQ8_0Runs great9.3 GB5.2
M2 Pro · 16 GBQ6_K_LRuns great7.6 GB10
M2 Pro · 32 GBQ8_0Runs great9.3 GB10
M2 Max · 32 GBQ8_0Runs great9.3 GB19
M2 Max · 64 GBQ8_0Runs great9.3 GB19
M2 Max · 96 GBQ8_0Runs great9.3 GB19
M2 Ultra · 64 GBQ8_0Runs great9.3 GB34
M2 Ultra · 128 GBQ8_0Runs great9.3 GB34
M2 Ultra · 192 GBQ8_0Runs great9.3 GB34
M1 · 8 GBQ3_K_LRuns well5.3 GB4.4
M1 · 16 GBQ6_K_LRuns great7.6 GB3.5
M1 Pro · 16 GBQ6_K_LRuns great7.6 GB9.7
M1 Pro · 32 GBQ8_0Runs great9.3 GB9.6
M1 Max · 32 GBQ8_0Runs great9.3 GB18
M1 Max · 64 GBQ8_0Runs great9.3 GB18
M1 Ultra · 64 GBQ8_0Runs great9.3 GB30
M1 Ultra · 128 GBQ8_0Runs great9.3 GB30

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

Information

Maker
Cohere
Released
October 2024
Parameters
8B
Longest chat
8K tokens
Reads pictures
No
Licence
cc-by-nc-4.0
Downloads this month
6,576
Likes
47
Sizes
24, 3.1 to 16 GB
Kind
Maker's release

Badge for the model card

Shows on Aya Expanse 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