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
signalnine
/
Qwen3.6-27B-MTP-q27
like
1
q27
quantized
speculative-decoding
mtp
qwen3.6
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
Qwen3.6-27B-MTP-q27
145 GB
Ctrl+K
Ctrl+K
1 contributor
History:
21 commits
signalnine
retitle: seven tiers, 4.55-8.1 bpw
943775e
verified
about 2 months ago
.gitattributes
Safe
1.98 kB
add q5f/q6f tiers: qwen36-27b-mtp-q6f.q27
about 2 months ago
CHECKSUMS.md5
446 Bytes
add q5f/q6f tiers: CHECKSUMS.md5
about 2 months ago
README.md
6.71 kB
retitle: seven tiers, 4.55-8.1 bpw
about 2 months ago
qwen36-27b-mtp-q4s.q27
Safe
15.5 GB
xet
Upload qwen36-27b-mtp-q4s.q27 with huggingface_hub
about 2 months ago
qwen36-27b-mtp-q5f.q27
Safe
18.2 GB
xet
add q5f/q6f tiers: qwen36-27b-mtp-q5f.q27
about 2 months ago
qwen36-27b-mtp-q6.q27
Safe
20.5 GB
xet
q6-v1 tier: 6.0 bits/param (v1.4 + ffn_down Q8), PPL 7.946 vs Q5_K_M bar 7.918 (+0.35%; 5.25bpw is +1.55%)
about 2 months ago
qwen36-27b-mtp-q6f.q27
Safe
21 GB
xet
add q5f/q6f tiers: qwen36-27b-mtp-q6f.q27
about 2 months ago
qwen36-27b-mtp-q6k.q27
Safe
23.3 GB
xet
q6k-v1 tier: 6.8 bits/param (q6 + ffn_gate Q8), PPL 7.9127
about 2 months ago
qwen36-27b-mtp-q8.q27
Safe
28.5 GB
xet
q8-v1 tier: full Q8_G128 (28.45 GB, ~8.1 bpw) -- 48GB+ cards; UNVALIDATED pending the ladder on 48GB-class hardware
about 2 months ago
qwen36-27b-mtp.q27
Safe
17.7 GB
xet
Upload qwen36-27b-mtp.q27 with huggingface_hub
2 months ago
qwen36-27b-mtp.tok
Safe
7.21 MB
xet
Upload qwen36-27b-mtp.tok with huggingface_hub
2 months ago