Open-weight model
GLM-5.3-Flash-TensorFold-Runtime
by Andy Stewart manateelazycat/GLM-5.3-Flash-TensorFold-Runtime
GLM-5.3-Flash-TensorFold-Runtime is an open-weight model from Andy Stewart, released under other. Its published files total 18.6 GB.
This is a Docker-save runtime archive for two NVIDIA Thor T5000 nodes with driver 595.78 and SM 11.0. It contains no model weights. Download the target and DFlash2 snapshots separately from the manateelazycat model repositories.
Model Card
This is a Docker-save runtime archive for two NVIDIA Thor T5000 nodes with driver 595.78 and SM 11.0. It contains no model weights. Download the target and DFlash2 snapshots separately from the manateelazycat model repositories. The corresponding LPK uses the selected Hugging Face / ModelScope source for both model files and this archive. Public downloads require no hub login. The historical 0.5.0 reference environment was TensorFold 0.6.1 plus Mia 1.3.2 with the validated Thor decoder and communication patches. Default capacity is 1,048,576 tokens per request, a 2,684,928-token shared KV pool, and four streams. Reference acceptance includes empty-cache CUDA JIT, vision, structured output…
Excerpt from the card by Andy Stewart, licensed other.
Identity and Version
- Repository
- manateelazycat/GLM-5.3-Flash-TensorFold-Runtime
- Publisher
- Andy Stewart
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- 6019fdd0d2217cc04821a74a03b39fe537dad1e2
- First published
- 2026-10-01
- Last updated
- 2026-10-14
Files and Weights
22 files, 18.6 GB in total.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| release-0.5.0.json | Configuration | 8.2 KB | — |
| release-0.5.1.json | Configuration | 9.7 KB | — |
| release-0.5.2.json | Configuration | 11.4 KB | — |
| runtime-manifest.json | Configuration | 9.5 KB | — |
| PERFORMANCE-0.5.0.md | Documentation | 7.4 KB | — |
| PERFORMANCE-0.5.1.md | Documentation | 6.0 KB | — |
| PERFORMANCE-0.5.2.md | Documentation | 4.7 KB | — |
| README.md | Documentation | 3.9 KB | — |
| SHA256SUMS | Other | 113 B | — |
| SHA256SUMS-0.5.0 | Other | 276 B | — |
| SHA256SUMS-0.5.1 | Other | 276 B | — |
| SHA256SUMS-0.5.2 | Other | 276 B | — |
| cloud.lazycat.aipod.glm53f-v0.5.0.lpk | Other | 6.6 MB | ed87f47f96da |
| cloud.lazycat.aipod.glm53f-v0.5.1.lpk | Other | 6.6 MB | c55fa05b790b |
| cloud.lazycat.aipod.glm53f-v0.5.2.lpk | Other | 6.6 MB | d1fd3cda35c4 |
| glm-5.3-flash-dual-t5000-runtime-0.4.1.tar.gz | Other | 2.8 GB | 3968c00c6ab0 |
| glm-5.3-flash-dual-t5000-runtime-0.5.0.tar.gz | Other | 3.2 GB | fd8b05e226c7 |
| glm-5.3-flash-dual-t5000-runtime-0.5.1.tar.gz | Other | 3.2 GB | cdc137c2289a |
| glm-5.3-flash-dual-t5000-runtime-0.5.10.tar.gz | Other | 3.2 GB | d63e72ff40df |
| glm-5.3-flash-dual-t5000-runtime-0.5.14.tar.gz | Other | 3.2 GB | 38e8275d1060 |
| glm-5.3-flash-dual-t5000-runtime-0.5.4.tar.gz | Other | 3.2 GB | 83e0b5afbe8b |
| .gitattributes | Repository | 1.9 KB | — |
License and Download
- License
- other
- Access
- Open weights, no gate
Released by Andy Stewart through its official repository on Hugging Face.
Questions About GLM-5.3-Flash-TensorFold-Runtime
What license is GLM-5.3-Flash-TensorFold-Runtime released under?
other, as its publisher declares it. Read the license text before commercial use.