Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
embedl
/
Cosmos-Reason2-2B-W4A16-Edge2
like
12
Follow
Embedl
48
Image-Text-to-Text
Cosmos
Safetensors
qwen3_vl
nvidia
cosmos-reason2
multimodal
vlm
quantized
edge
llmcompressor
mixed-precision
conversational
compressed-tensors
License:
embedl-models-community-licence-1.0
Model card
Files
Files and versions
xet
Community
Use this model
main
Cosmos-Reason2-2B-W4A16-Edge2
2.19 GB
Ctrl+K
Ctrl+K
4 contributors
History:
47 commits
HProg
Embed hfviewer card in model card
ba1f812
verified
13 days ago
.gitattributes
Safe
1.57 kB
Upload W4A16 mixed model (exclude recipe yaml)
about 2 months ago
README.md
Safe
8.62 kB
Embed hfviewer card in model card
13 days ago
added_tokens.json
Safe
707 Bytes
Upload W4A16 mixed model (exclude recipe yaml)
about 2 months ago
chat_template.jinja
Safe
5.29 kB
Upload W4A16 mixed model (exclude recipe yaml)
about 2 months ago
chat_template.json
Safe
5.5 kB
Make quantization more robust
about 1 month ago
config.json
Safe
7.35 kB
Make quantization more robust
about 1 month ago
generation_config.json
Safe
269 Bytes
Make quantization more robust
about 1 month ago
merges.txt
Safe
1.67 MB
Make quantization more robust
about 1 month ago
model.safetensors
Safe
2.18 GB
xet
Make quantization more robust
about 1 month ago
preprocessor_config.json
Safe
390 Bytes
Upload W4A16 mixed model (exclude recipe yaml)
about 2 months ago
special_tokens_map.json
Safe
613 Bytes
Upload W4A16 mixed model (exclude recipe yaml)
about 2 months ago
tokenizer.json
Safe
7.03 MB
xet
Make quantization more robust
about 1 month ago
tokenizer_config.json
Safe
10.9 kB
Make quantization more robust
about 1 month ago
video_preprocessor_config.json
Safe
385 Bytes
Make quantization more robust
about 1 month ago
vocab.json
Safe
2.78 MB
Upload W4A16 mixed model (exclude recipe yaml)
about 2 months ago
