Qwen3-Reranker-4B-W4A16-G128 vs ms-marco-MiniLM-L-6-v2
Specs, VRAM requirements and download trends — updated 21 September 2026.
boboliu · A
Params
4.1 B
Context
40,960
30d
586 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3-Reranker-4B-W4A16-G128 | ms-marco-MiniLM-L-6-v2 |
|---|---|---|
| Parameters | 4.1 B | — |
| Architecture | Qwen3ForCausalLM | BertForSequenceClassification |
| Context length | 40,960 | 512 |
| Licence | apache-2.0 | — |
| Commercial use | Allowed | Unknown |
| Languages | — | — |
| Downloads 30d | 585,788 | 1,026,158 |
| Downloads all time | 2.9 M | 2.2 M |
| Quantizations on the Hub | SAFETENSORS | — |
| Gated | No | No |
| First seen on the Hub | 2025-06-07 | 2024-01-04 |
Download trend
Daily snapshots, last 56 days (28 Jul – 21 Sep)
1.2 M250 K
Qwen3-Reranker-4B-W4A16-G128
ms-marco-MiniLM-L-6-v2
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3-Reranker-4B-W4A16-G128 · fp16
4.0 GB / 24 GB
Adjacent comparisons
bge-reranker-v2-m3 vs ms-marco-MiniLM-L-6-v2
finbert vs ms-marco-MiniLM-L-6-v2
Prompt-Guard-86M vs ms-marco-MiniLM-L-6-v2
bge-reranker-base vs ms-marco-MiniLM-L-6-v2
distilbert-base-uncased-finetuned-sst-2-english vs ms-marco-MiniLM-L-6-v2
twitter-roberta-base-sentiment-latest vs ms-marco-MiniLM-L-6-v2