vntl-llama3-8b-v2-gguf vs madlad400-3b-mt
Specs, VRAM requirements and download trends — updated 6 August 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | vntl-llama3-8b-v2-gguf | madlad400-3b-mt |
|---|---|---|
| Parameters | — | 2.9 B |
| Architecture | — | T5ForConditionalGeneration |
| Context length | — | — |
| Licence | llama3 | apache-2.0 |
| Commercial use | Conditional | Allowed |
| Languages | 2 | 419 |
| Downloads 30d | 774,149 | 266,782 |
| Downloads all time | 5.7 M | 4.4 M |
| Quantizations on the Hub | GGUF | GGUF, SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2025-01-02 | 2023-11-27 |
Download trend
Daily snapshots, last 10 days (28 Jul – 6 Aug)
782 K230 K
vntl-llama3-8b-v2-gguf
madlad400-3b-mt
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
madlad400-3b-mt · fp16
13.9 GB / 24 GB