Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
pytorch
/
Qwen3-4B-INT8-INT4
like
2
Follow
pytorch
307
Text Generation
Transformers
PyTorch
multilingual
qwen3
torchao
qwen
nlp
code
math
chat
conversational
text-generation-inference
arxiv:
2507.16099
License:
mit
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
c10a6f4
Qwen3-4B-INT8-INT4
12.5 GB
2 contributors
History:
20 commits
jerryzh168
Update README.md
c10a6f4
verified
8 months ago
.gitattributes
1.76 kB
Rename qwen3-4b-8da4w-1024-ctx.pte to qwen3-4B-8da4w-1024-cxt.pte
8 months ago
README.md
9.97 kB
Update README.md
8 months ago
added_tokens.json
707 Bytes
Upload tokenizer
8 months ago
chat_template.jinja
4.12 kB
Upload tokenizer
8 months ago
config.json
3.02 kB
Upload Qwen3ForCausalLM
8 months ago
generation_config.json
219 Bytes
Upload Qwen3ForCausalLM
8 months ago
merges.txt
1.67 MB
Upload tokenizer
8 months ago
pytorch_model.bin
4.79 GB
xet
Upload Qwen3ForCausalLM
8 months ago
pytorch_model_converted.bin
4.79 GB
xet
Rename qwen3-4b-converted.bin to pytorch_model_converted.bin
8 months ago
qwen3-4B-8da4w-1024-cxt.pte
2.91 GB
xet
Rename qwen3-4b-8da4w-1024-ctx.pte to qwen3-4B-8da4w-1024-cxt.pte
8 months ago
special_tokens_map.json
613 Bytes
Upload tokenizer
8 months ago
tokenizer.json
11.4 MB
xet
Upload tokenizer
8 months ago
tokenizer_config.json
5.4 kB
Upload tokenizer
8 months ago
vocab.json
2.78 MB
Upload tokenizer
8 months ago
