all-MiniLM-L6-v2-onnx vs nomic-embed-code
Specs, VRAM requirements and download trends — updated 1 November 2026.
Qdrant · A · Open weights
Params
—
Context
512
30d
1.6 M
apache-2.0 · commercial OK
nomic-ai · B · Open weights
Params
7.1 B
Context
32,768
30d
356 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | all-MiniLM-L6-v2-onnx | nomic-embed-code |
|---|---|---|
| Parameters | — | 7.1 B |
| Architecture | BertModel | Qwen2Model |
| Context length | 512 | 32,768 |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | — |
| Downloads 30d | 1,601,209 | 356,168 |
| Downloads all time | 12.7 M | 3.2 M |
| Quantizations on the Hub | — | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2024-01-16 | 2025-03-24 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
1.7 M356 K
all-MiniLM-L6-v2-onnx
nomic-embed-code
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
nomic-embed-code · fp16
32.7 GB / 24 GB