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
plunderstruck
/
Qwen3.6-27B-MTP-ROCmFP4-GGUF
like
30
GGUF
rocmfp4
qwen3.6
mtp
speculative-decoding
strix-halo
amd
rocm
vulkan
License:
other
Model card
Files
Files and versions
xet
Community
4
Copy to bucket
new
main
Qwen3.6-27B-MTP-ROCmFP4-GGUF
18.7 GB
Ctrl+K
Ctrl+K
1 contributor
History:
30 commits
plunderstruck
Repoint build instructions to charlie12345/ROCmFPX (ROCmFPX FP3/4/6/8 repo)
9752475
verified
about 1 month ago
.gitattributes
Safe
1.91 kB
Add mmproj-F32.gguf (best-of-both / vision)
about 2 months ago
Qwen3.6-27B-MTP-ROCmFP4-STRIX-imatrix-embF16-headQ6.gguf
Safe
16.9 GB
xet
Add Q6-head variant (output.weight -> Q6_K): more faithful, ~5-7% slower decode
about 2 months ago
README.md
Safe
36.5 kB
Repoint build instructions to charlie12345/ROCmFPX (ROCmFPX FP3/4/6/8 repo)
about 1 month ago
chat_template.jinja
Safe
14.1 kB
Add froggeric v20 fixed chat template (vision + inline think-toggle + tool anti-stall); use via --chat-template-file
about 2 months ago
mmproj-F32.gguf
1.84 GB
xet
Add mmproj-F32.gguf (best-of-both / vision)
about 2 months ago
qwen3.6-27b-code.imatrix
Safe
13.6 MB
xet
Upload qwen3.6-27b-code.imatrix with huggingface_hub
about 2 months ago
