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
hipfire-models
/
qwen3.5-4b-dev
like
0
Follow
Hipfire
6
English
hipfire
quantization
lloyd-max
research
qwen3.5
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
qwen3.5-4b-dev
7.76 GB
Ctrl+K
Ctrl+K
1 contributor
History:
6 commits
kread
add 4B MQ4 + AWQ + GPTQ + Q8 conv1d quant (KLD 0.0662 / PPL 10.71 @ n=512 q8-KV)
f34f01e
verified
16 days ago
mq4-awq-gptq-q8conv
add 4B MQ4 + AWQ + GPTQ + Q8 conv1d quant (KLD 0.0662 / PPL 10.71 @ n=512 q8-KV)
16 days ago
.gitattributes
Safe
1.72 kB
add 4B MQ4 + AWQ + GPTQ + Q8 conv1d quant (KLD 0.0662 / PPL 10.71 @ n=512 q8-KV)
16 days ago
README.md
Safe
5.43 kB
README: add MQ4-Lloyd variant + correct repo path to -dev
23 days ago
qwen3.5-4b.mq3-lloyd
2.25 GB
xet
Add qwen3.5-4b.mq3-lloyd (Phase A research quant)
23 days ago
qwen3.5-4b.mq4-lloyd
2.92 GB
xet
Add qwen3.5-4b.mq4-lloyd (Phase B WMMA prefill research quant, PR #197)
23 days ago
