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
vcruz305
/
Qwen3.8-Flash-Next-GGUF
like
1
GGUF
qwen
qwen3.8
flash-next
llama.cpp
mtp
k-quant
License:
other
Model card
Files
Files and versions
xet
Community
3
Copy to bucket
new
main
Qwen3.8-Flash-Next-GGUF
538 GB
Ctrl+K
Ctrl+K
1 contributor
History:
36 commits
vcruz305
gguf: Q6_K backbone 00001-00006 (MTP in-main)
e2926cd
verified
5 days ago
MTP
MTP: draft GGUFs BF16 Q8_0 Q4_K_M only
5 days ago
PLE-BF16
PLE: shared BF16 per_layer_token_embd (~95GiB)
5 days ago
Q2_K
gguf: Q2_K backbone 00001-00006 (MTP in-main)
5 days ago
Q3_K_M
gguf: Q3_K_M backbone 00001-00006 (MTP in-main)
5 days ago
Q4_K_M
gguf: Q4_K_M backbone 00001-00006 (MTP in-main)
5 days ago
Q5_K_M
gguf: Q5_K_M backbone 00001-00006 (MTP in-main)
5 days ago
Q6_K
gguf: Q6_K backbone 00001-00006 (MTP in-main)
5 days ago
imatrix
imatrix: AtomicChat-based imatrix.gguf
5 days ago
scripts
scripts: link-ple.sh
5 days ago
.gitattributes
4.51 kB
gguf: Q6_K backbone 00001-00006 (MTP in-main)
5 days ago
README.md
Safe
1.84 kB
docs: full K-ladder Q2-Q6 with MTP + shared BF16 PLE
5 days ago
