Linlunson

linlunson's activity

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

updated a collection 13 days ago

strata rtx4090 48gb *3

Collection

CPU: AMD 7950X 16C/32T, GPU: NVIDIA RTX4090*3, VRAM: 144GB, RAM: DDR5 256GB • 4 items • Updated 13 days ago

New activity in ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF 13 days ago

qwen3.8-flash-next-gsq-iq3_s vs qwen3.8-flash-next-unsloth-ud-iq4_xs (3090-24g)

👍 4

1

#49 opened about 1 month ago by

XTTAI

updated a collection 26 days ago

strata rtx4090 48gb *3

Collection

CPU: AMD 7950X 16C/32T, GPU: NVIDIA RTX4090*3, VRAM: 144GB, RAM: DDR5 256GB • 4 items • Updated 13 days ago

New activity in SC117/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF about 1 month ago

Qwen3.8 125B A6B · Dual RTX 4090 48G Layer-Split — Optimal Configuration and Measured Performance

🔥 1

1

#2 opened about 1 month ago by

linlunson

updated a collection about 1 month ago

strata rtx4090 48gb *3

Collection

CPU: AMD 7950X 16C/32T, GPU: NVIDIA RTX4090*3, VRAM: 144GB, RAM: DDR5 256GB • 4 items • Updated 13 days ago

liked a model about 1 month ago

ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF

Image-Text-to-Text • 177B • Updated Sep 29 • 7M • 1.22k

New activity in SC117/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF about 1 month ago

Thanks — Swift-1.5 abliterated on an 8 GB laptop: it works, and the MTP numbers

🔥 1

4

#1 opened about 1 month ago by

dbshark

liked a model about 1 month ago

IndexTeam/Index-Echo-S2ST-2B-GGUF

Translation • 2B • Updated 27 days ago • 1.37k • 4

updated a collection about 1 month ago

rkllm rk-llama.cpp rk3588s_16gb

Collection

https://github.com/airockchip/rknn-llm/ https://github.com/invisiofficial/rk-llama.cpp/ • 5 items • Updated Oct 6