Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
RESMP-DEV
/
GLM-4.7-Flash-Trellis-MM
like
1
Follow
RESMP.DEV
15
Text Generation
Transformers
Safetensors
Trellis
English
Chinese
glm4_moe_lite
quantized
Mixture of Experts
3-bit
mixed-precision
cuda
glm
metal-marlin
8-bit precision
arxiv:
2508.06471
License:
mit
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
GLM-4.7-Flash-Trellis-MM
16.2 GB
1 contributor
History:
3 commits
Kearm
Update README.md
7162e09
verified
9 days ago
.gitattributes
1.57 kB
Upload folder using huggingface_hub
9 days ago
README.md
5.49 kB
Update README.md
9 days ago
base_weights.safetensors
1.28 GB
xet
Upload folder using huggingface_hub
9 days ago
config.json
1.07 kB
Upload folder using huggingface_hub
9 days ago
model-00001-of-00007.safetensors
2.15 GB
xet
Upload folder using huggingface_hub
9 days ago
model-00002-of-00007.safetensors
2.15 GB
xet
Upload folder using huggingface_hub
9 days ago
model-00003-of-00007.safetensors
2.15 GB
xet
Upload folder using huggingface_hub
9 days ago
model-00004-of-00007.safetensors
2.15 GB
xet
Upload folder using huggingface_hub
9 days ago
model-00005-of-00007.safetensors
2.15 GB
xet
Upload folder using huggingface_hub
9 days ago
model-00006-of-00007.safetensors
2.15 GB
xet
Upload folder using huggingface_hub
9 days ago
model-00007-of-00007.safetensors
2.04 GB
xet
Upload folder using huggingface_hub
9 days ago
model.safetensors.index.json
3.81 MB
Upload folder using huggingface_hub
9 days ago
quantization_index.json
2.02 MB
Upload folder using huggingface_hub
9 days ago
tokenizer.json
20.2 MB
xet
Upload folder using huggingface_hub
9 days ago
tokenizer_config.json
7.23 kB
Upload folder using huggingface_hub
9 days ago
