casperhansen PRO

casperhansen's activity

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

New activity in cognitivecomputations/DeepSeek-R1-AWQ about 2 months ago

The inference performance of the DeepSeek-R1-AWQ model is weak compared to the DeepSeek-R1 model

8

#3 opened 2 months ago by

qingqingz916

updated 6 models about 2 months ago

casperhansen/deepseek-r1-distill-qwen-1.5b-awq

Updated Feb 8 • 2.05k • 3

casperhansen/deepseek-r1-distill-qwen-7b-awq

Updated Feb 8 • 8.72k • 9

casperhansen/deepseek-r1-distill-llama-8b-awq

Updated Feb 8 • 757 • 2

casperhansen/deepseek-r1-distill-qwen-14b-awq

Updated Feb 8 • 6.24k • 13

casperhansen/deepseek-r1-distill-llama-70b-awq

Updated Feb 8 • 1.81k • 14

casperhansen/deepseek-r1-distill-qwen-32b-awq

Updated Feb 8 • 7.03k • 10

updated a model 2 months ago

casperhansen/mistral-small-24b-instruct-2501-awq

Updated Jan 30 • 3.05k • 7

published a model 2 months ago

casperhansen/mistral-small-24b-instruct-2501-awq

Updated Jan 30 • 3.05k • 7

New activity in casperhansen/deepseek-r1-distill-qwen-32b-awq 2 months ago

Generation configs: Unquantised vs AWQ, model weights format

3

#1 opened 3 months ago by

nfunctor

updated a collection 3 months ago

DeepSeek R1 AWQ

Collection

7 items • Updated Jan 22 • 5

published 3 models 3 months ago

casperhansen/deepseek-r1-distill-llama-70b-awq

Updated Feb 8 • 1.81k • 14

casperhansen/deepseek-r1-distill-qwen-32b-awq

Updated Feb 8 • 7.03k • 10

casperhansen/deepseek-r1-distill-qwen-14b-awq

Updated Feb 8 • 6.24k • 13