Instructions to use ninfer-5080/Qwen3.8-27B-RTX5080 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NInfer
How to use ninfer-5080/Qwen3.8-27B-RTX5080 with NInfer:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
docs: add release provenance
Browse files- PROVENANCE.md +58 -0
PROVENANCE.md
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
Release provenance
|
| 3 |
+
Official distribution
|
| 4 |
+
repository:
|
| 5 |
+
ninfer-5080/Qwen3.8-27B-RTX5080
|
| 6 |
+
|
| 7 |
+
artifact:
|
| 8 |
+
qwen3_8_27b.ninfer
|
| 9 |
+
Artifact identity
|
| 10 |
+
bytes:
|
| 11 |
+
16461267456
|
| 12 |
+
|
| 13 |
+
SHA256:
|
| 14 |
+
c4a7e9ab593a7f42d58208fa0065d67a82d61921107686cc9f6ed1ec6b050e21
|
| 15 |
+
Validated production runtime
|
| 16 |
+
NInfer source:
|
| 17 |
+
ceb32f7d002edab224a83a2e2609f45fca4f8919
|
| 18 |
+
|
| 19 |
+
ninfer-serve SHA256:
|
| 20 |
+
3179bfbcb88a72c04b983f28c25c62db468fbc8ef267fe043899de30a4281c56
|
| 21 |
+
Source models
|
| 22 |
+
Qwen/Qwen3.8-27B
|
| 23 |
+
1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0
|
| 24 |
+
|
| 25 |
+
z-lab/Qwen3.8-27B-DFlash2
|
| 26 |
+
50307d4c4cde6860d4eee73e2547cd786fe8e8a4
|
| 27 |
+
Official publication
|
| 28 |
+
|
| 29 |
+
The project-owned Hugging Face artifact was published on 2026-09-21 only after
|
| 30 |
+
the local model size/SHA and validated v1.3 ninfer-serve SHA were rechecked.
|
| 31 |
+
|
| 32 |
+
Initial model publication commit:
|
| 33 |
+
|
| 34 |
+
4120bd9a68cf2d2829c5f6b83ace8c9280b4b823
|
| 35 |
+
|
| 36 |
+
GitHub documentation/provenance update merged at:
|
| 37 |
+
|
| 38 |
+
e8a84d133f7a9fc02c507dbfb870e752ae810788
|
| 39 |
+
|
| 40 |
+
Canonical technical record:
|
| 41 |
+
|
| 42 |
+
https://github.com/toddballinger/ninfer-5080
|
| 43 |
+
|
| 44 |
+
Artifact/runtime separation
|
| 45 |
+
|
| 46 |
+
The .ninfer model artifact and the NInfer runtime are deliberately tracked
|
| 47 |
+
separately.
|
| 48 |
+
|
| 49 |
+
Subsequent runtime optimizations may continue to use this exact model SHA.
|
| 50 |
+
A new runtime source commit should not be interpreted as a new model release
|
| 51 |
+
unless the artifact byte size or SHA-256 changes.
|
| 52 |
+
|
| 53 |
+
Automated reproduction
|
| 54 |
+
|
| 55 |
+
CPU-only automated conversion/publication is being integrated separately.
|
| 56 |
+
|
| 57 |
+
A workflow claiming byte-identical reproduction should hard-fail unless the
|
| 58 |
+
generated artifact matches the canonical byte size and SHA-256 above.
|