clap-htsat-unfused vs Qwen3-VL-Embedding-8B-FP8
Specs, VRAM requirements and download trends — updated 27 September 2026.
RamManavalan · B · Open weights
Params
8.8 B
Context
—
30d
407 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | clap-htsat-unfused | Qwen3-VL-Embedding-8B-FP8 |
|---|---|---|
| Parameters | — | 8.8 B |
| Architecture | ClapModel | Qwen3VLForConditionalGeneration |
| Context length | — | — |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | 8 |
| Downloads 30d | 953,794 | 407,360 |
| Downloads all time | 9.8 M | 1.2 M |
| Quantizations on the Hub | — | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2023-02-16 | 2026-01-22 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
1.4 M407 K
clap-htsat-unfused
Qwen3-VL-Embedding-8B-FP8
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3-VL-Embedding-8B-FP8 · fp16
13.5 GB / 24 GB