Jose Marcalo

JigSawPT's activity

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

New activity in deepseek-ai/DeepSeek-V4.1-Flash 4 days ago

Runs on one RTX 5090 (31.8 GiB) + 125.7 GiB RAM via a llama.cpp fork: GGUF, report and numbers

🔥 5

4

#37 opened 16 days ago by

JigSawPT

New activity in JigSawPT/DeepSeek-V4.1-Flash-GGUF 4 days ago

Request of a Q2 quantization in the "antirez" style?

🚀 1

1

#3 opened 12 days ago by

automacellulare

Laptop RTX5090 (24GB vRAM) + 64GBRam + RAID0 Gen4 -> 3.45 token/sec

5

#2 opened 13 days ago by

aydintb

I am going try this MXFP4 quant on 4 TITAN X, 12.2, GTX 960 4GB + 330GiB DDR3 + Samsung m.2 NVME for the checkpoint.

3

#4 opened 10 days ago by

BigDeeper

updated a model 5 days ago

JigSawPT/DeepSeek-V4.1-Flash-GGUF

755B • Updated 4 days ago • 1.69k • 7

New activity in JigSawPT/DeepSeek-V4.1-Flash-DSpark-GGUF 12 days ago

DeepSeek-V4.1-Flash Suggestion

3

#1 opened 15 days ago by

TheRealRalphWiggum

updated a model 13 days ago

JigSawPT/DeepSeek-V4.1-Flash-DSpark-GGUF

14B • Updated 13 days ago • 3.51k • 4

New activity in JigSawPT/DeepSeek-V4.1-Flash-DSpark-GGUF 13 days ago

Keep the target's token_embd unquantized: +4–5 points of acceptance

1

#2 opened 14 days ago by

midagedev

New activity in JigSawPT/DeepSeek-V4.1-Flash-GGUF 16 days ago

How this GGUF runs on one RTX 5090, and the numbers behind it

👍 2

2

#1 opened 16 days ago by

JigSawPT

published 2 models 16 days ago

JigSawPT/DeepSeek-V4.1-Flash-GGUF

755B • Updated 4 days ago • 1.69k • 7

JigSawPT/DeepSeek-V4.1-Flash-DSpark-GGUF

14B • Updated 13 days ago • 3.51k • 4

liked a model 25 days ago

empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF

Image-Text-to-Text • 9B • Updated Jul 14 • 533k • 2.77k

updated a dataset 3 months ago

JigSawPT/ptpt-failure-set-gate

Viewer • Updated Jul 5 • 240 • 93

published a dataset 3 months ago

JigSawPT/ptpt-failure-set-gate

Viewer • Updated Jul 5 • 240 • 93