all-MiniLM-L6-v2 vs gte-Qwen2-1.5B-instruct
Specs, VRAM requirements and download trends — updated 21 September 2026.
sentence-transformers · A
Params
20 M
Context
512
30d
252.2 M
apache-2.0 · commercial OK
Alibaba-NLP · B
Params
1.8 B
Context
131,072
30d
665 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | all-MiniLM-L6-v2 | gte-Qwen2-1.5B-instruct |
|---|---|---|
| Parameters | 20 M | 1.8 B |
| Architecture | BertModel | Qwen2ForCausalLM |
| Context length | 512 | 131,072 |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | 1 | — |
| Downloads 30d | 252,170,882 | 664,667 |
| Downloads all time | 3.9 B | 7.9 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2022-03-02 | 2024-06-29 |
Download trend
Daily snapshots, last 56 days (28 Jul – 21 Sep)
259.7 M665 K
all-MiniLM-L6-v2
gte-Qwen2-1.5B-instruct
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
all-MiniLM-L6-v2 · fp16
0.6 GB / 24 GB
gte-Qwen2-1.5B-instruct · fp16 @ 128K ctx
12.6 GB / 24 GB