vntl-llama3-8b-v2-gguf vs TowerInstruct-13B-v0.1
Specs, VRAM requirements and download trends — updated 22 August 2026.
lmg-anon · A · Open weights
Params
—
Context
—
30d
28 K
llama3 licence · conditional
Unbabel · B · Open weights
Params
13.0 B
Context
4,096
30d
49 K
cc-by-nc-4.0 · non-commercial
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | vntl-llama3-8b-v2-gguf | TowerInstruct-13B-v0.1 |
|---|---|---|
| Parameters | — | 13.0 B |
| Architecture | — | LlamaForCausalLM |
| Context length | — | 4,096 |
| Licence | llama3 | cc-by-nc-4.0 |
| Commercial use | Conditional | Not allowed |
| Languages | 2 | 10 |
| Downloads 30d | 27,658 | 48,961 |
| Downloads all time | 6.1 M | 124 K |
| Quantizations on the Hub | GGUF | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2025-01-02 | 2024-01-29 |
Download trend
Daily snapshots, last 89 days (28 Jul – 24 Oct)
782 K28 K
vntl-llama3-8b-v2-gguf
TowerInstruct-13B-v0.1
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
TowerInstruct-13B-v0.1 · fp16
59.7 GB / 24 GB