Luke Chen

LukeC110's activity

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

New activity in unsloth/Qwen3.8-Flash-Next-GGUF about 12 hours ago

Question about loading the model with RTX 4090 and RTX 6000 pro?

7

#22 opened about 13 hours ago by

LukeC110

New activity in unsloth/Qwen3.8-Flash-Next-GGUF about 20 hours ago

Is it possible to offload n-gram to an NVMe SSD?

👀🚀 31

14

#11 opened about 22 hours ago by

lingyezhixing

New activity in deepseek-ai/DeepSeek-V4-Flash-0731 11 days ago

Grabage token looping issue

👍 1

#65 opened 11 days ago by

LukeC110

New activity in unsloth/DeepSeek-V4-Flash-0731-GGUF 16 days ago

DAE know how to corretly run DSpark with part of the model offloaded to RAM using llama.cpp?

3

#40 opened 19 days ago by

LukeC110

New activity in deepseek-ai/DeepSeek-V4-Flash-0731 21 days ago

PSA If you have terrible looping issues or random character generations try update your CUDA to 13.3

1

#46 opened 21 days ago by

LukeC110

This model has many tool_call errors.

5

#45 opened 21 days ago by

Gureumi

Reasoning loops

➕ 3

22

#39 opened 23 days ago by

d3lavar

New activity in unsloth/DeepSeek-V4-Flash-0731-GGUF 23 days ago

3bit working, 4bit not

👍 4

3

#12 opened 26 days ago by

tasticleeze