Meta-Llama-3-8B vs Meta-Llama-3.1-8B-Instruct
Specs, VRAM requirements and download trends — updated 21 August 2026.
meta-llama · A · Open weights
Params
8.0 B
Context
—
30d
139 K
llama3 licence · conditional
unsloth · B · Open weights
Params
8.0 B
Context
131,072
30d
169 K
llama3.1 licence · conditional
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Meta-Llama-3-8B | Meta-Llama-3.1-8B-Instruct |
|---|---|---|
| Parameters | 8.0 B | 8.0 B |
| Architecture | LlamaForCausalLM | LlamaForCausalLM |
| Context length | — | 131,072 |
| Licence | llama3 | llama3.1 |
| Commercial use | Conditional | Conditional |
| Languages | 1 | 1 |
| Downloads 30d | 139,310 | 169,484 |
| Downloads all time | 47.3 M | 7.1 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | Yes — accept licence | No |
| First seen on the Hub | 2024-04-17 | 2024-07-23 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
1.9 M139 K
Meta-Llama-3-8B
Meta-Llama-3.1-8B-Instruct
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Meta-Llama-3-8B · fp16
19.4 GB / 24 GB
Meta-Llama-3.1-8B-Instruct · fp16 @ 128K ctx
37.4 GB / 24 GB