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
agiws
/
Qwen3.8-27B-NQ-UD-IQ2-M
Like
0
Follow
AGI Workshop
1
GGUF
quantization
iq2_m
ud
experimental
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
Qwen3.8-27B-NQ-UD-IQ2-M
/
src
/
agiws_neural_quant
/
kquant
565 kB
Ctrl+K
Ctrl+K
1 contributor
History:
5 commits
ArGrigorov
kquant unchanged (v0.6.5)
dc5d512
verified
21 days ago
__pycache__
kquant unchanged (v0.6.5)
21 days ago
__init__.py
Safe
14.8 kB
kquant source (vectorized packers) for reproducibility
22 days ago
_gguf_bits.py
Safe
1.13 kB
kquant source (vectorized packers) for reproducibility
22 days ago
_iq_tables.py
Safe
139 kB
kquant source (vectorized packers) for reproducibility
22 days ago
gguf_pack.py
Safe
20.7 kB
fix iq2_s qh int64->uint8 (packer byte width); v0.5.7
22 days ago
gguf_packed.py
Safe
11.5 kB
kquant source (vectorized packers) for reproducibility
22 days ago
gguf_packed_q2q3.py
Safe
5.51 kB
kquant source (vectorized packers) for reproducibility
22 days ago
gguf_plan.py
2.37 kB
plan: output.weight Q5_K->Q4_K (Q5_K packer broken cos=0.69); v0.6.2
22 days ago
iq.py
Safe
45.7 kB
fix iq2_s qh int64->uint8 (packer byte width); v0.5.7
22 days ago
