Paul Cozzolino PRO

pastapaul's activity

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

New activity in canada-quant/GLM-5.2-W4A16-MTP 13 days ago

Loading the model

4

#1 opened 16 days ago by

madeby561

updated a model 13 days ago

canada-quant/GLM-5.2-W4A16-MTP

Text Generation • 116B • Updated 13 days ago • 7.17k • 17

New activity in canada-quant/GLM-5.2-W4A16-MTP 15 days ago

Can you run NVFP4 + Marlin?

5

#2 opened 16 days ago by

einsteiner1983

updated a Space 16 days ago

Running

Canada Quant Labs

🍁

liked a model 16 days ago

canada-quant/GLM-5.2-W4A16-MTP

Text Generation • 116B • Updated 13 days ago • 7.17k • 17

published a model 18 days ago

canada-quant/GLM-5.2-W4A16-MTP

Text Generation • 116B • Updated 13 days ago • 7.17k • 17

New activity in canada-quant/DeepSeek-V4-Flash-NVFP4-FP8-MTP about 1 month ago

Docker Image

8

#1 opened about 2 months ago by

mtcl

New activity in canada-quant/DeepSeek-V4-Flash-W4A16-FP8 about 1 month ago

Compatible version with Ampere? SM8.6

1

#6 opened about 2 months ago by

bullerwins

Small patch to fix MTP on current vLLM (8th of June, 26)

7

#8 opened about 1 month ago by

dnhkng

New activity in canada-quant/DeepSeek-V4-Flash-W4A16-FP8-MTP about 1 month ago

MTP BF16 draft weights may need explicit quant_config exclusion for vLLM

2

#2 opened about 1 month ago by

yangsiqt2

vLLM compressed-tensors loader fails on shared_experts.gate_up_proj — missing quant target for fused shared-expert projection?

3

#1 opened about 1 month ago by

ajdoosh

updated a model about 1 month ago

canada-quant/DeepSeek-V4-Flash-W4A16-FP8-MTP

Text Generation • 51B • Updated May 30 • 6.39k • 18

updated a dataset about 2 months ago

canada-quant/dsv4-flash-w4a16-rtxpro6000-image

Updated May 30 • 143 • 3

published a dataset about 2 months ago

canada-quant/dsv4-flash-w4a16-rtxpro6000-image

Updated May 30 • 143 • 3

updated a model about 2 months ago

canada-quant/DeepSeek-V4-Flash-NVFP4-FP8-MTP

171B • Updated May 29 • 1.83k • 8

New activity in canada-quant/DeepSeek-V4-Flash-W4A16-FP8 about 2 months ago

2026-05-26 dual-spark bench: GSM8K 94-98%, AIME 4/5, concurrency wall 12→125 tok/s

#7 opened about 2 months ago by

pastapaul

New activity in canada-quant/DeepSeek-V4-Pro-NVFP4-FP8-MTP about 2 months ago

Lossless?

👀 1

1

#1 opened about 2 months ago by

lukealonso

updated a model about 2 months ago

canada-quant/DeepSeek-V4-Pro-NVFP4-FP8-MTP

922B • Updated May 26 • 256 • 4

New activity in canada-quant/DeepSeek-V4-Flash-W4A16-FP8 about 2 months ago

Does the Redhat accuracy loss concern apply here also?

1

#5 opened about 2 months ago by

1anH

updated a model about 2 months ago

canada-quant/DeepSeek-V4-Flash-W4A16-FP8

Text Generation • 44B • Updated May 25 • 4.64k • 16