Lauro Carvalho

wonderfuldestruction's activity

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

liked 2 models 3 days ago

Boogu/Boogu-Image-0.1-Edit-Turbo-fp8

Image-to-Image • Updated 13 days ago • 418 • 16

ethanfel/Qwen3-VL-32B-Ultra-Heretic-H3-ComfyUI-INT8-ConvRot

Image-Text-to-Text • Updated about 23 hours ago • 325

liked a model 4 days ago

UnstableLlama/Semancer-27B

28B • Updated 22 days ago • 123 • 3

New activity in nvidia/Qwen3.6-27B-NVFP4 18 days ago

Has anyone got this same CUDA error: an illegal memory access was encountered while using this model in vllm:v0.25.0?

2

#20 opened 22 days ago by

lzachary

liked a model about 1 month ago

DJLougen/Qwable-5-27B-Coder-NVFP4

Text Generation • 15B • Updated Jun 23 • 610 • 10

liked a model 3 months ago

froggeric/Qwen-Fixed-Chat-Templates

Updated Jul 3 • 1.03k

liked 3 models 4 months ago

unsloth/Qwen3.6-27B-GGUF

Image-Text-to-Text • 27B • Updated Apr 22 • 608k • 928

byteshape/Qwen3.5-35B-A3B-GGUF

Image-Text-to-Text • 35B • Updated Apr 13 • 1.3k • 33

Tesslate/OmniCoder-9B

Text Generation • 9B • Updated Mar 13 • 1.41k • 672

liked a model 5 months ago

Tesslate/OmniCoder-9B-GGUF

9B • Updated Mar 12 • 8.61k • 324

New activity in ubergarm/Qwen3.5-27B-GGUF 5 months ago

Appraisal

🔥 1

5

#6 opened 5 months ago by

wonderfuldestruction

liked 2 models 5 months ago

ubergarm/Qwen3.5-27B-GGUF

Text Generation • 27B • Updated Apr 24 • 72 • 18

apolo13x/Qwen3.5-27B-NVFP4

Image-Text-to-Text • 17B • Updated Feb 27 • 2.52k • 39

New activity in byteshape/Devstral-Small-2-24B-Instruct-2512-GGUF 5 months ago

Very good quant

🚀 3

5

#1 opened 6 months ago by

wonderfuldestruction

liked a model 6 months ago

byteshape/Devstral-Small-2-24B-Instruct-2512-GGUF

Text Generation • 24B • Updated Feb 18 • 992 • 28

New activity in noctrex/GLM-4.7-Flash-MXFP4_MOE-GGUF 6 months ago

BF16 has looping issues

28

#4 opened 6 months ago by

jmander11

reacted to danielhanchen's post with 🔥🤗 6 months ago

view post

Post

5300

We collaborated with Hugging Face to enable you to train MoE models 12× faster with 35% less VRAM via our new Triton kernels (no accuracy loss). 🤗

Train gpt-oss locally on 12.8GB VRAM with our free notebooks: https://unsloth.ai/docs/new/faster-moe

See translation

• 
• 

• 
• 1 reply

·

🔥

29

29

🤗

5

5

+

Reply

liked 2 models 6 months ago

Virtue-AI-HUB/VulnLLM-R-7B

Text Generation • 8B • Updated Dec 12, 2025 • 50.7k • • 234

Qwen/Qwen3-Coder-Next

Text Generation • 80B • Updated Feb 3 • 537k • • 1.57k