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
Unsloth AI
Team
company
Verified
https://unsloth.ai
UnslothAI
unslothai
unsloth
Activity Feed
Follow
32,511
AI & ML interests
Run and train models via Unsloth Desktop 🦥
Recent Activity
shimmyshimmer
new
activity
2 days ago
unsloth/Qwen3.8-27B-GGUF:
Why Qwen3.8-27B-UD-Q8_K_XL.gguf is not updated like other quants?
shimmyshimmer
new
activity
2 days ago
unsloth/Qwen3.8-27B-GGUF:
What's the use of mtp-Qwen3.8-27B-Q4_0.gguf?
shimmyshimmer
new
activity
2 days ago
unsloth/Qwen3.8-27B-GGUF:
Crash using UD V3 on dual RDNA4 Cards
View all activity
Team members
2
unsloth
's activity
All
Models
Datasets
Spaces
Buckets
Papers
Collections
Community
Posts
Articles
shimmyshimmer
in
unsloth/Qwen3.8-27B-GGUF
2 days ago
Why Qwen3.8-27B-UD-Q8_K_XL.gguf is not updated like other quants?
6
#91 opened 3 days ago by
akierum
What's the use of mtp-Qwen3.8-27B-Q4_0.gguf?
7
#97 opened 3 days ago by
cnayan01
Crash using UD V3 on dual RDNA4 Cards
1
#98 opened 2 days ago by
rusty20080
V3 versions of UD-Q3_K_XL and UD-Q4_K_XL feel way less competent than before / Can you upload the older variants as well?
4
#99 opened 2 days ago by
RudieVoeller
We need to talk about the aliyuncs.com symptom
1
#62 opened 7 days ago by
owao
Small Quants with integrated MTP dont make sense
👍
4
4
#37 opened 9 days ago by
TheWegemann
All UD- GGUFs in this repo have wrong general.file_type metadata
🔥
➕
3
2
#38 opened 9 days ago by
Phenomellama
Q4_K_M gets wrong output using kobold.cpp
6
#55 opened 8 days ago by
Blizado
How is this even possible? Qwen 3.8 exceeding 256K?
#64 opened 7 days ago by
sa13ma
Missing IMatrix file
👍
9
2
#17 opened 9 days ago by
signsur4739379373
imatrix dataset?
2
#82 opened 4 days ago by
Basher17
Why delete Qwen3.8-27B-IQ4_NL.gguf with huggingface_hub?
👍
5
3
#86 opened 4 days ago by
puchuu
Model latest memory date
1
#85 opened 4 days ago by
XeroSeNse
q2kxl
2
#93 opened 3 days ago by
deleted
Why top 1 as a main metric?
❤️
2
#96 opened 3 days ago by
NikiKrutan
danielhanchen
in
unsloth/Qwen3.8-27B-GGUF
2 days ago
New UD-Q8-K-L bigger than Q8_0 but less accurate?
2
#92 opened 3 days ago by
rosspanda0
danielhanchen
in
unsloth/Qwen3.8-27B-GGUF
3 days ago
Imatrix now available!
🔥
🚀
14
1
#88 opened 3 days ago by
danielhanchen
Introducing Unsloth Dynamic v3 Qwen3.8
👍
🔥
45
32
#74 opened 4 days ago by
danielhanchen
danielhanchen
updated
a model
3 days ago
unsloth/Qwen3.8-27B-GGUF
27B
•
Updated
3 days ago
•
6.67M
•
2.73k
danielhanchen
in
unsloth/Qwen3.8-27B-GGUF
3 days ago
Even at low Q6 quant it's very good!
🤗
2
1
#84 opened 4 days ago by
auf1r2
Load more