Luke Chen

LukeC110's activity

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

New activity in turboderp/Qwen3.8-Flash-Next-exl3 16 days ago

Does this support ngram nvme offloading for people with 32GB system RAM?

4

#3 opened 16 days ago by

LukeC110

New activity in unsloth/Qwen3.8-Flash-Next-GGUF 22 days ago

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

7

#22 opened 22 days ago by

LukeC110

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

👀🚀 31

15

#11 opened 22 days ago by

lingyezhixing

New activity in deepseek-ai/DeepSeek-V4-Flash-0731 about 1 month ago

Grabage token looping issue

👍 1

#65 opened about 1 month ago by

LukeC110

New activity in unsloth/DeepSeek-V4-Flash-0731-GGUF about 1 month ago

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

3

#40 opened about 1 month ago by

LukeC110

New activity in deepseek-ai/DeepSeek-V4-Flash-0731 about 1 month ago

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

1

#46 opened about 1 month ago by

LukeC110

This model has many tool_call errors.

5

#45 opened about 1 month ago by

Gureumi

Reasoning loops

➕ 3

22

#39 opened about 1 month ago by

d3lavar

New activity in unsloth/DeepSeek-V4-Flash-0731-GGUF about 1 month ago

3bit working, 4bit not

👍 4

3

#12 opened about 2 months ago by

tasticleeze