Ollama · aya-expanse

<img src="https://ollama.com/assets/library/aya-expanse/fba5fdd1-f5f3-43d2-a2e1-04c9e37d37be" width="460" /> Aya Expanse represents a significant advancement in multilingual AI capabilities. Combinin…

ollama/aya-expanse

<img src="https://ollama.com/assets/library/aya-expanse/fba5fdd1-f5f3-43d2-a2e1-04c9e37d37be" width="460" />

Aya Expanse represents a significant advancement in multilingual AI capabilities. Combining Cohere's Command model family with a year of focused research in multilingual optimization has produced versatile 8B and 32B parameter models that can understand and generate text across 23 languages while maintaining high performance across all of them.

## Key Features - 8-billion and 32-billion parameter multilingual language models developed by Cohere For AI - Supports Arabic, Chinese (simplified & traditional), Czech, Dutch, English, French, German, Greek, Hebrew, Hebrew, Hindi, Indonesian, Italian, Japanese, Korean, Persian, Polish, Portuguese, Romanian, Russian, Spanish, Turkish, Ukrainian, and Vietnamese - Built on the Command family of models with extensive research in data arbitrage, multilingual preference training, and safety tuning - 128K context length - Released under CC-BY-NC license with additional usage policies

## References [Blog post](https://cohere.com/blog/aya-expanse-connecting-our-world)

[HuggingFace](https://huggingface.co/CohereForAI/aya-expanse-8b)

Specifications & capabilities

Published model ID
aya-expanse

Deployments & artifacts

1–20 / 33

ollama

source id
ollama
execution mode
local
parameter size
32.3B
parameter count
32300000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
8000
context window is approximate
true
artifact size bytes
19800850336
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
32.3B
parameter count
32300000000
parameter count is approximate
true
quantization level
F16
context window
8000
context window is approximate
true
artifact size bytes
64604536736
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
32.3B
parameter count
32300000000
parameter count is approximate
true
quantization level
Q2_K
context window
8000
context window is approximate
true
artifact size bytes
12810780576
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
32.3B
parameter count
32300000000
parameter count is approximate
true
quantization level
Q3_K_L
context window
8000
context window is approximate
true
artifact size bytes
17563451296
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
32.3B
parameter count
32300000000
parameter count is approximate
true
quantization level
Q3_K_M
context window
8000
context window is approximate
true
artifact size bytes
16231759776
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
32.3B
parameter count
32300000000
parameter count is approximate
true
quantization level
Q3_K_S
context window
8000
context window is approximate
true
artifact size bytes
14708703136
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
32.3B
parameter count
32300000000
parameter count is approximate
true
quantization level
Q4_0
context window
8000
context window is approximate
true
artifact size bytes
18719506336
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
32.3B
parameter count
32300000000
parameter count is approximate
true
quantization level
Q4_1
context window
8000
context window is approximate
true
artifact size bytes
20606943136
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
32.3B
parameter count
32300000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
8000
context window is approximate
true
artifact size bytes
19800850336
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
32.3B
parameter count
32300000000
parameter count is approximate
true
quantization level
Q4_K_S
context window
8000
context window is approximate
true
artifact size bytes
18849529760
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
32.3B
parameter count
32300000000
parameter count is approximate
true
quantization level
Q5_0
context window
8000
context window is approximate
true
artifact size bytes
22494379936
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
32.3B
parameter count
32300000000
parameter count is approximate
true
quantization level
Q5_1
context window
8000
context window is approximate
true
artifact size bytes
24381816736
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
32.3B
parameter count
32300000000
parameter count is approximate
true
quantization level
Q5_K_M
context window
8000
context window is approximate
true
artifact size bytes
23051435936
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
32.3B
parameter count
32300000000
parameter count is approximate
true
quantization level
Q5_K_S
context window
8000
context window is approximate
true
artifact size bytes
22494379936
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
32.3B
parameter count
32300000000
parameter count is approximate
true
quantization level
Q6_K
context window
8000
context window is approximate
true
artifact size bytes
26505183136
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
32.3B
parameter count
32300000000
parameter count is approximate
true
quantization level
Q8_0
context window
8000
context window is approximate
true
artifact size bytes
34326904736
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
8.0B
parameter count
8000000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
8000
context window is approximate
true
artifact size bytes
5056999552
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
8.0B
parameter count
8000000000
parameter count is approximate
true
quantization level
F16
context window
8000
context window is approximate
true
artifact size bytes
16067244160
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
8.0B
parameter count
8000000000
parameter count is approximate
true
quantization level
Q2_K
context window
8000
context window is approximate
true
artifact size bytes
3438522496
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
8.0B
parameter count
8000000000
parameter count is approximate
true
quantization level
Q3_K_L
context window
8000
context window is approximate
true
artifact size bytes
4527992960
updated at
2026-11-16T08:10:06.079865+00:00

Original sources

1–2 / 2

Ollama · Model page ↗

Ollama · Catalog ↗

Source links

1–1 / 1

Explore more models

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace