Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
YSLAB-ai
/
Qwen3.8-Flash-Next-NVFP4-BF16PLE-DGX-Spark
Like
0
vllm
qwen
dgx-spark
nvme
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
0bae7d5
Qwen3.8-Flash-Next-NVFP4-BF16PLE-DGX-Spark
/
src
143 kB
Ctrl+K
Ctrl+K
1 contributor
History:
4 commits
YSLAB-ai
Mark BF16 MTP overlay runtime-qualified
d6ddb10
verified
22 days ago
recipe
Mark BF16 MTP overlay runtime-qualified
22 days ago
patch_parallel_lm_head_linear_attrs.py
Safe
1.43 kB
Publish DGX Spark BF16 PLE recipe
22 days ago
patch_qwen4_exp_config.py
Safe
1.53 kB
Publish DGX Spark BF16 PLE recipe
22 days ago
patch_qwen4_exp_mtp_compressed_ignore.py
Safe
1.8 kB
Publish BF16 MTP overlay recipe and qualification results
22 days ago
patch_qwen4_exp_mtp_load_guard.py
Safe
6.08 kB
Publish BF16 MTP overlay recipe and qualification results
22 days ago
patch_qwen4_exp_quantized_lm_head.py
Safe
1.64 kB
Publish DGX Spark BF16 PLE recipe
22 days ago
test_ple_mmap_cpu.py
Safe
10.8 kB
Publish DGX Spark BF16 PLE recipe
22 days ago
vllm_ple_mmap.py
Safe
21.9 kB
Publish DGX Spark BF16 PLE recipe
22 days ago
