Llama-3.1-8B-Instruct vs EXAONE-3.5-7.8B-Instruct

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

meta-llama · A
Params
8.0 B
Context
30d
8.0 M
llama3.1 licence · conditional
LGAI-EXAONE · B
Params
7.8 B
Context
32,768
30d
518 K

Specification comparison

Differences are highlighted; identical values are muted.

Specification Llama-3.1-8B-Instruct EXAONE-3.5-7.8B-Instruct
Parameters 8.0 B 7.8 B
Architecture LlamaForCausalLM ExaoneForCausalLM
Context length 32,768
Licence llama3.1 other
Commercial use Conditional Unknown
Languages 8 2
Downloads 30d 8,014,793 518,320
Downloads all time 175.3 M 3.2 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated Yes — accept licence No
First seen on the Hub 2024-07-18 2024-12-01

Download trend

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

8.0 M507 K
Llama-3.1-8B-Instruct EXAONE-3.5-7.8B-Instruct

VRAM side by side

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

Llama-3.1-8B-Instruct · fp16 19.4 GB / 24 GB
✅ Runs comfortably
EXAONE-3.5-7.8B-Instruct · fp16 36.1 GB / 24 GB
❌ Won’t fit

Adjacent comparisons