Hugging Face's logo

embedl
/
Cosmos-Reason2-8B-W4A16-FlashHead

Image-Text-to-Text
Cosmos
Safetensors
qwen3_vl
nvidia
cosmos-reason2
multimodal
vlm
quantized
flashhead
conversational
compressed-tensors
Model card Files
xet
 Community
Cosmos-Reason2-8B-W4A16-FlashHead

Commit History

Add Discord support banner to model card
78f93f3
verified

Magzimilian commited on

Add Embedl banner to top of model card
e93b39c
verified

Magzimilian commited on

Add Discord support banner to model card
b99f760
verified

Magzimilian commited on

Add privacy-policy notice to gated access prompt
28c3cbd
verified

Magzimilian commited on

Add voluntary Company field to gate form
fd0b446
verified

Magzimilian commited on

Add clickable Edge Inference Benchmarks screenshot to README
cf59633

Jonna Marie Matthiesen Claude Opus 4.6 (1M context) commited on

Update README: migrate workflow from embedl-models to flash-head
fcac823

Jonna Marie Matthiesen Claude Opus 4.6 (1M context) commited on

Migrate to flash-head package: remove custom model files and auto_map
e824fce

Jonna Marie Matthiesen Claude Opus 4.6 (1M context) commited on

Add configuration_flash_head_qwen3_vl.py for FlashHead support
c616588
verified

WilhelmT commited on

Add modeling_flash_head_qwen3_vl.py for FlashHead support
08691a7
verified

WilhelmT commited on

Add config.json for FlashHead support
c2511c7
verified

WilhelmT commited on

Add FlashHead assets and update config
2903c4b
verified

WilhelmT commited on

initial commit
587dec8
verified

WilhelmT commited on