Ondřej Plátek

oplatek's activity

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

New activity in bottlecapai/ThinkingCap-Qwen3.6-27B-FP8 about 4 hours ago

sglang support

2

#3 opened 2 days ago by

Alex123563

Fix for vLLM Loading Crash on Ampere/Ada GPUs (TP=8, RuntimeError: size_n = 12)

4

#2 opened 4 days ago by

MadGoatHaz

Deployment Note: vLLM JIT Path Resolution -nvidia/cu13/lib/-

2

#5 opened about 4 hours ago by

MadGoatHaz

updated a model about 4 hours ago

bottlecapai/ThinkingCap-Qwen3.6-27B-FP8

Image-Text-to-Text • 28B • Updated about 4 hours ago • 9.42k • 12

New activity in bottlecapai/ThinkingCap-Qwen3.6-27B-GGUF about 8 hours ago

Does it even work?

15

#6 opened about 19 hours ago by

sa13ma

New activity in bottlecapai/ThinkingCap-Qwen3.6-27B about 9 hours ago

ThinkingCap-Qwen3.6-27B - Without Q8_XL Quant to match Unsloth this is waste of time sorry.

7

#9 opened 7 days ago by

akierum

New activity in bottlecapai/ThinkingCap-Qwen3.6-27B-FP8 2 days ago

vllm loaded with error

4

#1 opened 5 days ago by

wac81

liked a model 8 days ago

bottlecapai/ThinkingCap-Qwen3.6-27B

Image-Text-to-Text • 27B • Updated 5 days ago • 6.21k • • 364

New activity in bottlecapai/ThinkingCap-Qwen3.6-27B 8 days ago

lower safetensors quants

❤️ 1

4

#1 opened 9 days ago by

MalyVitalosnik

updated a model 12 days ago

bottlecapai/ThinkingCap-Qwen3.6-27B-GGUF

Image-Text-to-Text • 27B • Updated about 12 hours ago • 320k • 112

published a model 15 days ago

bottlecapai/ThinkingCap-Qwen3.6-27B-GGUF

Image-Text-to-Text • 27B • Updated about 12 hours ago • 320k • 112

liked a model 8 months ago

FluidInference/parakeet-tdt-0.6b-v3-coreml

Automatic Speech Recognition • Updated Apr 30 • 365k • 47

upvoted a paper 9 months ago

OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM

Paper • 2510.15870 • Published Oct 17, 2025 • 93

liked a model 10 months ago

fixie-ai/ultraVAD

Feature Extraction • Updated Jan 1 • 232k • 38

liked a model 11 months ago

microsoft/VibeVoice-1.5B

Text-to-Speech • 3B • Updated Jan 22 • 40.3k • 2.42k

liked 2 Spaces 11 months ago

Running

Featured

127

Open-LLM performances are plateauing, let’s make the leaderboard steep again

🏔

127

Explore and compare advanced language models on a new leaderboard

Running

3.94k

The Ultra-Scale Playbook

🌌

3.94k

The ultimate guide to training LLM on large GPU Clusters

liked a dataset 12 months ago

nvidia/Nemotron-Post-Training-Dataset-v1

Viewer • Updated Aug 25, 2025 • 25.7M • 8.44k • 185

liked a model about 1 year ago

Qwen/Qwen3-0.6B

Text Generation • 0.8B • Updated Jul 26, 2025 • 27.2M • • 1.41k

upvoted an article over 1 year ago

view article

Article

Mixture of Experts Explained

• 
• 
• +4

osanseviero, lewtun, philschmid, smangrul, ybelkada, pcuenq

•

Dec 11, 2023

• 1.16k