halt95/ThinkingCap-Qwen3.8-27B-W4A16-Merlin
Image-Text-to-Text • 27B • Updated • 503 • 4
Kieran
halt95
AI & ML interests
Squeezing the most out of hardware.
Recent Activity
updated a model 1 day ago
halt95/ThinkingCap-Qwen3.8-27B-W4A16-Merlin updated a model 1 day ago
halt95/Swift1.5-Huihui-Qwen3.8-Flash-Next-W4A16-Merlin updated a model 1 day ago
halt95/Swift1.5-Qwen3.8-Flash-Next-W4A16-MerlinOrganizations
None yet
updated 7
models 1 day ago
halt95/Swift1.5-Huihui-Qwen3.8-Flash-Next-W4A16-Merlin
Image-Text-to-Text • 124B • Updated • 573 • 5
halt95/Swift1.5-Qwen3.8-Flash-Next-W4A16-Merlin
Image-Text-to-Text • 124B • Updated • 383 • 5
halt95/Qwen3.8-27B-W4A16-Merlin
Image-Text-to-Text • 27B • Updated • 461 • 2
halt95/Ornith-1.5-122B-A10B-W4A16-Merlin
Image-Text-to-Text • 128B • Updated • 194 • 1
halt95/Nemotron-3.5-Super-VL-120B-A12B-W4A16-Merlin
Image-Text-to-Text • 129B • Updated • 237 • 2
halt95/Qwen3.8-Flash-Next-W4A16-Merlin
Image-Text-to-Text • 124B • Updated • 1.28k • 21
Swift 1.5 Variant
6
#1 opened about 1 month ago
by 
Goghor
updated a
model 8 days ago
Thank you so much for the quantization and for open-sourcing this!
❤️ 2
24
#3 opened about 2 months ago
by 
SongXiaoMao
published a
model 12 days ago
TP2 and PP2 would be interesting
35
#2 opened 2 months ago
by 
Neiko2002
published 2
models 23 days ago
liked a
model 24 days ago
published 2
models about 1 month ago
Please quantize Swift 1.5 too.
1
#4 opened about 1 month ago
by Goghor
Quantization Tips
1
#1 opened about 1 month ago
by Goghor
Please quantize Swift 1.5 too.
1
#4 opened about 1 month ago
by Goghor