Cool John

BernardCribbins's activity

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

New activity in Qwen/Qwen3.8-27B 4 days ago

Deployment & Performance Report: Qwen3.8-27B (BF16) on RTX PRO 6000 with SGLang + EAGLE

👍 5

2

#160 opened 5 days ago by

sssssong0814

New activity in Qwen/Qwen3.8-27B 7 days ago

A crazy thinking model

😔👍 12

23

#97 opened 11 days ago by

xuguowong

New activity in Qwen/Qwen3.8-27B 9 days ago

This model cannot stop thinking

➕🧠 4

4

#113 opened 10 days ago by

xvcy3w

qwen3.8-27b on one pro 6000: 140 tok/s, day after release

7

#101 opened 11 days ago by

Avifenesh

New activity in Qwen/Qwen3.8-27B 10 days ago

After waiting 49 minutes and 16 seconds while the model was still thinking, I'm simply giving up...

🧠👀 3

12

#92 opened 11 days ago by

MrDevolver

Follow-up: I benchmarked 45 llama.cpp settings on Qwen3.8-27B. The MTP draft head is worth 1.81x, free (RTX 5090, Q4_K_M)

🚀❤️ 9

1

#112 opened 10 days ago by

laxmimerit

context lenght can't set 1010000

4

#123 opened 10 days ago by

kuolung

It’s really good

🚀 6

3

#100 opened 11 days ago by

jbourny

New activity in Qwen/Qwen3.8-27B-FP8 12 days ago

LET'S GOOOOOO ❤️‍🔥🫶

🚀 2

1

#2 opened 12 days ago by

JSKitteh

New activity in ornith-ai/Ornith-1.0-35B-FP8 13 days ago

Performance on Ornith

#8 opened 13 days ago by

BernardCribbins

New activity in Qwen/Qwen3.6-35B-A3B-FP8 13 days ago

My benchmarks on this model on 4x RTX 5060 Ti 16GB

#17 opened 13 days ago by

BernardCribbins

how to quantize the model well?

1

#16 opened about 1 month ago by

Kekexu