Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
mconcat
/
Qwopus3.5-27B-v3-FP8-Dynamic
like
0
Text Generation
Transformers
Safetensors
English
Chinese
qwen3_5
image-text-to-text
qwen3.5
reasoning
quantized
fp8
fp8-dynamic
compressed-tensors
deltanet
chain-of-thought
mtp
conversational
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
1
Deploy
Use this model
main
Qwopus3.5-27B-v3-FP8-Dynamic
33.3 GB
Ctrl+K
Ctrl+K
1 contributor
History:
5 commits
mconcat
Add MTP layers to quantization_config.ignore list
a385d58
verified
about 15 hours ago
.gitattributes
Safe
1.57 kB
Upload folder using huggingface_hub
1 day ago
README.md
4.04 kB
Upload folder using huggingface_hub
1 day ago
chat_template.jinja
Safe
4.05 kB
Upload folder using huggingface_hub
1 day ago
config.json
20 kB
Add MTP layers to quantization_config.ignore list
about 15 hours ago
generation_config.json
Safe
142 Bytes
Upload folder using huggingface_hub
1 day ago
model.mtp.safetensors
Safe
849 MB
xet
Add MTP weights sidecar (BF16 from Qwen/Qwen3.5-27B)
about 15 hours ago
model.safetensors
32.4 GB
xet
Upload folder using huggingface_hub
1 day ago
model.safetensors.index.json
124 kB
Add sharded index with MTP tensor mappings
about 15 hours ago
preprocessor_config.json
Safe
482 Bytes
Upload folder using huggingface_hub
1 day ago
processor_config.json
Safe
1.3 kB
Upload folder using huggingface_hub
1 day ago
recipe.yaml
1.28 kB
Upload folder using huggingface_hub
1 day ago
tokenizer.json
Safe
20 MB
xet
Upload folder using huggingface_hub
1 day ago
tokenizer_config.json
Safe
1.17 kB
Upload folder using huggingface_hub
1 day ago
video_preprocessor_config.json
Safe
614 Bytes
Upload folder using huggingface_hub
1 day ago