ddww

dw1932

AI & ML interests

None yet

Recent Activity

new activity 2 days ago

Qwen/Qwen3.8-Flash-Next:Wow this is an outright killer model... anyone can now run this with mere 48 gb ram/vram & a fast nvme drive

published a Space 4 days ago

new activity 10 days ago

unsloth/DeepSeek-V4-Flash-0731-GGUF:Issues encountered when deploying UD-Q8_K_XL

View all activity

Organizations

None yet

New activity in Qwen/Qwen3.8-Flash-Next 2 days ago

Wow this is an outright killer model... anyone can now run this with mere 48 gb ram/vram & a fast nvme drive

#30 opened 3 days ago by

New activity in unsloth/DeepSeek-V4-Flash-0731-GGUF 10 days ago

Issues encountered when deploying UD-Q8_K_XL

#44 opened 17 days ago by

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

When deploying using UD-Q8_K_XL quantization, I encountered an issue where the model produces repetitive responses, preventing the task from stopping.

#45 opened 17 days ago by

New activity in deepseek-ai/DeepSeek-V4-Flash-0731 20 days ago

Here's how to run on SM120 / RTX 6000 Pro's (two of them) - not a troll/rickroll, I promise

#44 opened 25 days ago by

The depth-5 corruption reports were a serving-stack bug, not this model — resolution, guidance, and a small model-card suggestion

#50 opened 23 days ago by

New activity in fraserprice/DeepSeek-V4-Flash-DSpark about 2 months ago

Could you please tell me the differences between this model file and the official one?

#1 opened about 2 months ago by

New activity in lukealonso/MiniMax-M3-NVFP4 2 months ago

How accurate is the model?

#3 opened 2 months ago by

How accurate is the model?

#3 opened 2 months ago by