Qwen3-Embedding-4B-W4A16-G128 vs clap-htsat-unfused
Specs, VRAM requirements and download trends — updated 28 September 2026.
boboliu · A · Open weights
Params
4.1 B
Context
40,960
30d
414 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3-Embedding-4B-W4A16-G128 | clap-htsat-unfused |
|---|---|---|
| Parameters | 4.1 B | — |
| Architecture | Qwen3ForCausalLM | ClapModel |
| Context length | 40,960 | — |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | — |
| Downloads 30d | 413,817 | 953,794 |
| Downloads all time | 2.5 M | 9.8 M |
| Quantizations on the Hub | SAFETENSORS | — |
| Gated | No | No |
| First seen on the Hub | 2025-06-06 | 2023-02-16 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
1.4 M414 K
Qwen3-Embedding-4B-W4A16-G128
clap-htsat-unfused
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3-Embedding-4B-W4A16-G128 · fp16
4.0 GB / 24 GB