Llama-3.1-8B-Instruct vs aya-expanse-8b-AWQ

Specs, VRAM requirements and download trends — updated 6 August 2026.

meta-llama · A

Llama-3.1-8B-Instruct

Params

8.0 B

Context

—

30d

8.0 M

llama3.1 licence · conditional

Orion-zhen · B

aya-expanse-8b-AWQ

Params

9.1 B

Context

8,192

30d

198 K

Specification comparison

Differences are highlighted; identical values are muted.

Specification	Llama-3.1-8B-Instruct	aya-expanse-8b-AWQ
Parameters	8.0 B	9.1 B
Architecture	LlamaForCausalLM	CohereForCausalLM
Context length	—	8,192
Licence	llama3.1	gpl-3.0
Commercial use	Conditional	Unknown
Languages	8	23
Downloads 30d	8,014,793	197,579
Downloads all time	175.3 M	204 K
Quantizations on the Hub	SAFETENSORS	SAFETENSORS
Gated	Yes — accept licence	No
First seen on the Hub	2024-07-18	2024-10-26

Download trend

Daily snapshots, last 10 days (28 Jul – 6 Aug)

8.0 M198 K

Llama-3.1-8B-Instruct aya-expanse-8b-AWQ

VRAM side by side

On RTX 4090 · 24 GB · 8K context unless noted

aya-expanse-8b-AWQ · fp16 10.5 GB / 24 GB

✅ Runs comfortably

Llama-3.1-8B-Instruct · fp16 19.4 GB / 24 GB

✅ Runs comfortably

Adjacent comparisons

Qwen3-8B vs Llama-3.1-8B-Instruct

Qwen2.5-7B-Instruct vs Llama-3.1-8B-Instruct

Qwen3.6-35B-A3B-NVFP4 vs Llama-3.1-8B-Instruct

Llama-3.1-8B-Instruct vs Qwen2.5-7B-Instruct-AWQ

Llama-3.1-8B-Instruct vs granite-4.1-8b

gpt-oss-20b vs Llama-3.1-8B-Instruct