Downloads · 30 days
41
27% of all-time downloads
Jasper-Token-Compression-600M-ONNX-INT8
magiccodingman/Jasper-Token-Compression-600M-ONNX-INT8
Jasper-Token-Compression-600M-ONNX-INT8 is a sentence similarity model from magiccodingman. Use it when you need a score for how close two texts are. It is set up for sentence-transformers. The card lists the license as apache-2.0.
ONNX export of infgrad/Jasper-Token-Compression-600M.
All-time downloads
151
Public
Repo size
623 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.onnx612 MB · 97%
At a glance
- Task
- Sentence Similarity
- Library
- sentence-transformers
- License
- apache-2.0
- Model type
- qwen3
- Access
- Public
- Created
- Aug 11, 2026
- Updated
- Aug 11, 2026
- SHA
- 16121ff4
Base models
Model card
From the Hugging Face model README
Jasper Token Compression 600M — ONNX INT-8
ONNX export of infgrad/Jasper-Token-Compression-600M.
Precision: INT8 (Dynamic)
Quantization: Dynamic INT8
Model size: 583.56 MiB
Dynamic INT8 ONNX export optimized for fast CPU inference. This is a text embedding model.
Benchmarks
| Tokens | Median latency | Tokens/s |
|---|---|---|
| 32 | 44.362 ms | 721.3 |
| 128 | 48.609 ms | 2,633.3 |
| 512 | 63.180 ms | 8,103.8 |
| 1024 | 84.619 ms | 12,101.3 |
Fidelity
Median cosine similarity versus FP32: ~0.988–0.992.
Attribution
Original model: infgrad/Jasper-Token-Compression-600M
- Task
- Sentence Similarity
- Library
- sentence-transformers
- Type
- qwen3
- License
- apache-2.0
- Languages
- en, zh
- Created
- Aug 11, 2026
- Updated
- Aug 11, 2026