Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
kyaky
/
Qwen3.6-35B-A3B-NVFP4
like
1
Text Generation
Safetensors
qwen3_5_moe
nvfp4
fp4
llm-compressor
compressed-tensors
vllm
Mixture of Experts
quantized
conversational
8-bit precision
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
894cdfa
Qwen3.6-35B-A3B-NVFP4
22.5 GB
Ctrl+K
Ctrl+K
1 contributor
History:
2 commits
kyaky
NVFP4 self-quant (llm-compressor): FP8 attn/GDN + NVFP4-W4A16 experts; beats redhat/unsloth on quality+speed+size
894cdfa
verified
5 days ago
.gitattributes
Safe
1.57 kB
NVFP4 self-quant (llm-compressor): FP8 attn/GDN + NVFP4-W4A16 experts; beats redhat/unsloth on quality+speed+size
5 days ago
README.md
2.75 kB
NVFP4 self-quant (llm-compressor): FP8 attn/GDN + NVFP4-W4A16 experts; beats redhat/unsloth on quality+speed+size
5 days ago
benchmark.png
54.5 kB
NVFP4 self-quant (llm-compressor): FP8 attn/GDN + NVFP4-W4A16 experts; beats redhat/unsloth on quality+speed+size
5 days ago
chat_template.jinja
Safe
7.76 kB
NVFP4 self-quant (llm-compressor): FP8 attn/GDN + NVFP4-W4A16 experts; beats redhat/unsloth on quality+speed+size
5 days ago
config.json
588 kB
NVFP4 self-quant (llm-compressor): FP8 attn/GDN + NVFP4-W4A16 experts; beats redhat/unsloth on quality+speed+size
5 days ago
generation_config.json
Safe
214 Bytes
NVFP4 self-quant (llm-compressor): FP8 attn/GDN + NVFP4-W4A16 experts; beats redhat/unsloth on quality+speed+size
5 days ago
model.safetensors
22.5 GB
xet
NVFP4 self-quant (llm-compressor): FP8 attn/GDN + NVFP4-W4A16 experts; beats redhat/unsloth on quality+speed+size
5 days ago
preprocessor_config.json
Safe
390 Bytes
NVFP4 self-quant (llm-compressor): FP8 attn/GDN + NVFP4-W4A16 experts; beats redhat/unsloth on quality+speed+size
5 days ago
processor_config.json
Safe
1.19 kB
NVFP4 self-quant (llm-compressor): FP8 attn/GDN + NVFP4-W4A16 experts; beats redhat/unsloth on quality+speed+size
5 days ago
recipe.yaml
2.19 kB
NVFP4 self-quant (llm-compressor): FP8 attn/GDN + NVFP4-W4A16 experts; beats redhat/unsloth on quality+speed+size
5 days ago
tokenizer.json
Safe
20 MB
xet
NVFP4 self-quant (llm-compressor): FP8 attn/GDN + NVFP4-W4A16 experts; beats redhat/unsloth on quality+speed+size
5 days ago
tokenizer_config.json
Safe
1.12 kB
NVFP4 self-quant (llm-compressor): FP8 attn/GDN + NVFP4-W4A16 experts; beats redhat/unsloth on quality+speed+size
5 days ago
video_preprocessor_config.json
Safe
385 Bytes
NVFP4 self-quant (llm-compressor): FP8 attn/GDN + NVFP4-W4A16 experts; beats redhat/unsloth on quality+speed+size
5 days ago
