canada-quant/DeepSeek-V4-Flash-W4A16-FP8-MTP
Text Generation β’ 51B β’ Updated β’ 1.88k β’ 2
Paul Cozzolino PRO
pastapaul
AI & ML interests
None yet
Recent Activity
updated a model about 1 hour ago
canada-quant/DeepSeek-V4-Flash-W4A16-FP8-MTP new activity about 5 hours ago
canada-quant/DeepSeek-V4-Flash-NVFP4-FP8-MTP:Docker Image updated a dataset about 6 hours ago
canada-quant/dsv4-flash-w4a16-rtxpro6000-imageOrganizations
updated a
model about 1 hour ago
Docker Image
5
#1 opened 2 days ago
by 
mtcl
updated a
dataset about 6 hours ago
published a
dataset about 11 hours ago
updated a
model about 14 hours ago
2026-05-26 dual-spark bench: GSM8K 94-98%, AIME 4/5, concurrency wall 12β125 tok/s
#7 opened 3 days ago
by 
pastapaul
Lossless?
π 1
1
#1 opened 3 days ago
by 
lukealonso
updated a
model 3 days ago
Does the Redhat accuracy loss concern apply here also?
1
#5 opened 5 days ago
by 
1anH
updated a
model 5 days ago
liked 2
models 5 days ago
updated a
Space 6 days ago
published a
Space 6 days ago
published a
model 7 days ago
liked a
model 7 days ago
published a
model 7 days ago
published a
model 8 days ago
One shot bootstrap for 2 Sparks not working
1
#4 opened 14 days ago
by 
easonchow0419