blkpws
/

Qwen3.8-27B-NVFP4-IRIS-Cache-ObjectScript

Text Generation

8-bit precision

compressed-tensors

Model card Files Files and versions

Qwen3.8-27B-NVFP4-IRIS-Cache-ObjectScript

22 GB

Ctrl+K

Ctrl+K

1 contributor

History: 22 commits

blkpws's picture

README: add model-facts table + ~18B note

8ac0308 verified 8 days ago

.gitattributes

1.57 kB
publish tokenizer.json 9 days ago
README.md

2.3 kB
README: add model-facts table + ~18B note 8 days ago
chat_template.jinja

8.95 kB
canonical: chat_template.jinja (v5 weights) 8 days ago
config.json

10.5 kB
canonical: config.json (v5 weights) 8 days ago
generation_config.json

214 Bytes
publish generation_config.json 9 days ago
model-00001-of-00002.safetensors

19.4 GB
xet

canonical: model-00001-of-00002.safetensors (v5 weights) 8 days ago
model-00002-of-00002.safetensors

2.54 GB
xet

canonical: model-00002-of-00002.safetensors (v5 weights) 8 days ago
model.safetensors.index.json

152 kB
canonical: model.safetensors.index.json (v5 weights) 8 days ago
recipe.yaml

330 Bytes
canonical: recipe.yaml (v5 weights) 8 days ago
tokenizer.json

20 MB
xet

publish tokenizer.json 9 days ago
tokenizer_config.json

1.12 kB
publish tokenizer_config.json 9 days ago