Ex0bit
/

Qwen3.6-35B-A3B-PRISM-NVFP4

Text Generation

Mixture of Experts

compressed-tensors

Model card Files Files and versions

Qwen3.6-35B-A3B-PRISM-NVFP4

25.1 GB

Ctrl+K

Ctrl+K

1 contributor

History: 6 commits

Ex0bit's picture

Fix: rename model.language_model.visual.* -> model.visual.* in safetensors header

6e951cb verified about 1 month ago

.gitattributes

1.64 kB
Initial upload: PRISM-LITE-v4 NVFP4 W4A4 (25 GB, multimodal + MTP preserved) about 2 months ago
README.md

2.42 kB
Add README (PRISM-NVFP4) about 2 months ago
chat_template.jinja

7.76 kB
Initial upload: PRISM-LITE-v4 NVFP4 W4A4 (25 GB, multimodal + MTP preserved) about 2 months ago
config.json

23.2 kB
Initial upload: PRISM-LITE-v4 NVFP4 W4A4 (25 GB, multimodal + MTP preserved) about 2 months ago
generation_config.json

213 Bytes
Initial upload: PRISM-LITE-v4 NVFP4 W4A4 (25 GB, multimodal + MTP preserved) about 2 months ago
model.safetensors

23.4 GB
xet

Fix: rename model.language_model.visual.* -> model.visual.* in safetensors header about 1 month ago
model.safetensors.index.json

11.9 MB
xet

Fix: rename model.language_model.visual.* -> model.visual.* in safetensors header about 1 month ago
model_mtp.safetensors

1.69 GB
xet

Initial upload: PRISM-LITE-v4 NVFP4 W4A4 (25 GB, multimodal + MTP preserved) about 2 months ago
processor_config.json

1.19 kB
Initial upload: PRISM-LITE-v4 NVFP4 W4A4 (25 GB, multimodal + MTP preserved) about 2 months ago
tokenizer.json

20 MB
xet

Initial upload: PRISM-LITE-v4 NVFP4 W4A4 (25 GB, multimodal + MTP preserved) about 2 months ago
tokenizer_config.json

1.14 kB
Initial upload: PRISM-LITE-v4 NVFP4 W4A4 (25 GB, multimodal + MTP preserved) about 2 months ago