Chris Scott's picture

Chris Scott

getfit

·

AI & ML interests

None yet

Recent Activity

new activity 4 days ago

mlx-community/DeepSeek-V3-0324-4bit:Larger version?

liked a model 8 days ago

RedHatAI/Llama-4-Scout-17B-16E-Instruct-FP8-dynamic

liked a model 9 days ago

deepcogito/cogito-v1-preview-llama-70B

View all activity

Organizations

None yet

getfit's activity

New activity in mlx-community/DeepSeek-V3-0324-4bit 4 days ago

Larger version?

#2 opened 23 days ago by

New activity in meta-llama/Llama-4-Scout-17B-16E-Instruct 10 days ago

FP8 weights

#41 opened 11 days ago by

New activity in meta-llama/Llama-4-Scout-17B-16E-Instruct 12 days ago

Thank you!, Is it possible to run this with vLLM or sglang ?

#18 opened 12 days ago by

No one with a consumer grade GPU (< 32 vram) can run the lower L4 model... 😓

#20 opened 12 days ago by

UniversalLove333

New activity in Qwen/QwQ-32B about 1 month ago

missing opening <think>

#4 opened about 1 month ago by

New activity in qihoo360/TinyR1-32B-Preview about 2 months ago

Output repeating

#1 opened about 2 months ago by

New activity in Qwen/Qwen2.5-Coder-7B-Instruct 7 months ago

32b Coder

#5 opened 7 months ago by

New activity in Qwen/Qwen2.5-72B-Instruct 7 months ago

There's a HUGE drop in popular knowledge from v2 to v2.5.

#1 opened 7 months ago by