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
schuttdev
/
hipfire-qwen3.6-27b
like
9
hipfire
amd
rdna
quantized
qwen3.6
dflash
License:
mit
Model card
Files
Files and versions
xet
Community
3
Copy to bucket
new
main
hipfire-qwen3.6-27b
Ctrl+K
Ctrl+K
1 contributor
History:
10 commits
schuttdev
README: note AWQ-calibrated MQ4 reweights
f9b326a
verified
about 2 hours ago
.gitattributes
Safe
1.75 kB
Upload qwen3.6-27b.mq3 with huggingface_hub
27 days ago
README.md
4.01 kB
README: note AWQ-calibrated MQ4 reweights
about 2 hours ago
qwen3.6-27b.mq3
Safe
11.8 GB
xet
Upload qwen3.6-27b.mq3 with huggingface_hub
27 days ago
qwen3.6-27b.mq4
15 GB
xet
Replace MQ4 with AWQ-calibrated MQ4 (mi300x v3 trunk)
about 2 hours ago
qwen3.6-27b.mq4.triattn.blended_v3.bin
Safe
pickle
Pickle imports
No problematic imports detected
What is a pickle import?
2.36 MB
xet
Add v3 TriAttention sidecar (blended 1M corpus, R̄=0.610)
30 days ago
qwen36-27b-dflash-mq3.hfq
Safe
703 MB
xet
Upload qwen36-27b-dflash-mq3.hfq with huggingface_hub
27 days ago
qwen36-27b-dflash-mq4.hfq
Safe
919 MB
xet
refresh draft: z-lab/Qwen3.6-27B-DFlash@0919688 (2026-04-27); +4-11% tok/s vs 1dbb59a
about 1 month ago
