Meta-Llama-3-8B vs Mistral-7B-Instruct-v0.2-AWQ
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
TheBloke · B · Open weights
Params
7.2 B
Context
32,768
30d
205 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Meta-Llama-3-8B | Mistral-7B-Instruct-v0.2-AWQ |
|---|---|---|
| Parameters | 8.0 B | 7.2 B |
| Architecture | LlamaForCausalLM | MistralForCausalLM |
| Context length | — | 32,768 |
| Licence | llama3 | apache-2.0 |
| Commercial use | Conditional | Allowed |
| Languages | 1 | — |
| Downloads 30d | 139,310 | 204,977 |
| Downloads all time | 47.3 M | 3.1 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | Yes — accept licence | No |
| First seen on the Hub | 2024-04-17 | 2023-12-11 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
1.9 M139 K
Meta-Llama-3-8B
Mistral-7B-Instruct-v0.2-AWQ
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Mistral-7B-Instruct-v0.2-AWQ · fp16
6.2 GB / 24 GB
Meta-Llama-3-8B · fp16
19.4 GB / 24 GB