multilingual-e5-small vs LLM2Vec-Meta-Llama-3-8B-Instruct-mntp
Specs, VRAM requirements and download trends — updated 8 November 2026.
intfloat · A · Open weights
Params
120 M
Context
512
30d
9.4 M
mit · commercial OK
McGill-NLP · B · Open weights
Params
8.0 B
Context
8,192
30d
396 K
mit · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | multilingual-e5-small | LLM2Vec-Meta-Llama-3-8B-Instruct-mntp |
|---|---|---|
| Parameters | 120 M | 8.0 B |
| Architecture | BertModel | LlamaEncoderModel |
| Context length | 512 | 8,192 |
| Licence | mit | mit |
| Commercial use | Allowed | Allowed |
| Languages | 94 | 1 |
| Downloads 30d | 9,411,746 | 396,165 |
| Downloads all time | 130.6 M | 2.4 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2023-06-30 | 2024-04-30 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
12.6 M377 K
multilingual-e5-small
LLM2Vec-Meta-Llama-3-8B-Instruct-mntp
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
multilingual-e5-small · fp16
1.0 GB / 24 GB
LLM2Vec-Meta-Llama-3-8B-Instruct-mntp · fp16
1.9 GB / 24 GB