Willi Döring

wijjjj's activity

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

New activity in RadixArk/Qwen3.8-Flash-Next-NVFP4 15 days ago

Degeneration Loop when calling tool (PDF/Image)

🔥 1

4

#3 opened about 1 month ago by

dangnsh

New activity in cyankiwi/Qwen3.8-27B-AWQ-BF16-INT4 about 2 months ago

どうもありがとう

#3 opened about 2 months ago by

wijjjj

New activity in cyankiwi/Qwen3.8-27B-AWQ-INT4 about 2 months ago

Do AWQ-BF16-INT4

➕ 9

7

#1 opened about 2 months ago by

ab22k

New activity in cyankiwi/README about 2 months ago

Request for Qwen3.8-27B-AWQ-BF16-INT4

🔥 1

#14 opened about 2 months ago by

wijjjj

New activity in huginnfork/Qwen3.8-27B-FP8 2 months ago

nothingburger

👍 4

4

#1 opened 2 months ago by

wijjjj

New activity in protoLabsAI/Ornith-1.0-35B-FP8 3 months ago

Dual RTX 5090 test

👍 2

1

#1 opened 3 months ago by

SamirGFX

New activity in cyankiwi/Qwen3.6-35B-A3B-AWQ-4bit 3 months ago

Great fit for 2x4060 - 83tok/s

🤗🔥 8

2

#4 opened 6 months ago by

mrchuy

New activity in RedHatAI/gemma-4-26B-A4B-it-FP8-dynamic 6 months ago

KeyError: 'layers.0.experts.0.down_proj.weight' on vllm/vllm-openai:gemma4

👀➕ 5

13

#1 opened 6 months ago by

timbmg

New activity in cyankiwi/gemma-4-26B-A4B-it-AWQ-4bit 6 months ago

Use in OpenCode via vLLM: Endless Tool Calling Loops & undesirable behavior

12

#2 opened 6 months ago by

wijjjj

New activity in nvidia/Nemotron-Cascade-2-30B-A3B 7 months ago

Official quantizations?

👍 2

6

#9 opened 7 months ago by

wijjjj

New activity in mradermacher/Nemotron-Cascade-2-30B-A3B-i1-GGUF 7 months ago

Accetable results with i1-Q5_K_M or i1-Q6_0 ?

2

#1 opened 7 months ago by

wijjjj

New activity in TheBloke/CodeLlama-70B-hf-GGUF over 2 years ago

Problems with Q5_K_M variant using llama.cpp in terminal

5

#1 opened over 2 years ago by

wijjjj

Problems with Q5_K_M variant using llama.cpp in terminal

5

#1 opened over 2 years ago by

wijjjj