Andrey Aladzyev

puchuu's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in Qwen/Qwen3.8-27B 24 days ago

🏆 ROCM release v10.0 provided significant performance bonus

🤗 3

#186 opened 24 days ago by

puchuu

New activity in unsloth/Qwen3.8-27B-GGUF about 1 month ago

Intel Arc B70 results: 32 T/s with UD-Q6_K, SYCL, MTP

👍 2

3

#114 opened about 1 month ago by

Testererer

New activity in Qwen/Qwen3.8-27B about 1 month ago

🙏 The community needs Qwen 3.8 35B-A3B models and others, help us get there 🚀

➕❤️ 198

25

#120 opened about 1 month ago by

highpolygonal

New activity in unsloth/Qwen3.8-27B-GGUF about 1 month ago

Can i ask the sweet point for 12gb cards?

4

#81 opened about 1 month ago by

AsThirtyThree

Why delete Qwen3.8-27B-IQ4_NL.gguf with huggingface_hub?

👍 6

5

#86 opened about 1 month ago by

puchuu

Running Qwen3.8-27B Q4_K_S on an RTX 3060 12GB with 96K Context + MTP (~10 t/s)

👍 2

12

#61 opened about 1 month ago by

Hjx2

UD quants for 16GB VRAM?

7

#35 opened about 1 month ago by

Witherhoard

I think this model is not ready for use

👀👍 7

20

#40 opened about 1 month ago by

sa13ma

Dual 3080 20G, Q6-K_XL, avg 40 - 50 t/s

👍 1

6

#44 opened about 1 month ago by

xudongCNCS

tensor split crash

4

#43 opened about 1 month ago by

gregnetau

EXTREEEEMLY LOOOONG thinking block

6

#21 opened about 1 month ago by

Janumacky

Performance report on RTX 5090: 100 t/s with UD-Q6_K_XL

10

#14 opened about 1 month ago by

SlavikF

New activity in meta-models/Muse-Glimmer-30B about 2 months ago

Tutorial on how to run with llama.cpp

🤗👍 3

1

#53 opened about 2 months ago by

curiousily

New activity in Qwen/Qwen3.8-2.4T-A95B about 2 months ago

Why the hype?

👍 1

4

#8 opened about 2 months ago by

ElwinR

27b when?

🚀 10

17

#1 opened about 2 months ago by

tigerjjw53

New activity in meta-models/Muse-Glimmer-30B about 2 months ago

Even Big Lebowski doesn’t know where the money went: Meta’s "Superintelligence" is a sub-$5 basement-tier Frankenstein

🔥 17

17

#43 opened about 2 months ago by

Qozimo

MTP layer?

➕ 1

3

#45 opened about 2 months ago by

puchuu

New activity in unsloth/DeepSeek-V4-Flash-GGUF 3 months ago

Lower quants?

➕ 1

10

#2 opened 3 months ago by

Kelheor

New activity in unsloth/Qwen3-Coder-Next-GGUF 8 months ago

Feb 19: Qwen3-Coder-Next GGUFs update - much better outputs!

🤗👍 16

34

#5 opened 8 months ago by

danielhanchen

New activity in unsloth/MiniMax-M2.1-GGUF 9 months ago

Hot Damn This Model Cooks!

👍 6

12

#5 opened 9 months ago by

aaron-newsome