Jagat Kiran

jagat-primitive-org's activity

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

New activity in primitive-ai/Qwen3.8-Flash-Next-NVFP4 4 days ago

Field report: PLE-quant assets + SSD-Stream shell on a 62GB-RAM RTX 6000 Pro, KV pool up to 1,111,168

4

#2 opened 4 days ago by

AntigravityAI

New activity in primitive-ai/Qwen3.8-Flash-Next-PLE-quant 4 days ago

Optional resident mode for the quantized tables (VLLM_PLE_QUANT_RESIDENT)

2

#2 opened 4 days ago by

mgabor3141

updated 3 models 4 days ago

primitive-ai/Nex-N2.5-mini-FP8

Text Generation • 35B • Updated 4 days ago • 103

primitive-ai/Nex-N2.5-mini-NVFP4

Text Generation • 35B • Updated 4 days ago • 551

primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8

Text Generation • 21B • Updated 4 days ago • 578

published 3 models 5 days ago

primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8

Text Generation • 21B • Updated 4 days ago • 578

primitive-ai/Nex-N2.5-mini-FP8

Text Generation • 35B • Updated 4 days ago • 103

primitive-ai/Nex-N2.5-mini-NVFP4

Text Generation • 35B • Updated 4 days ago • 551

updated 2 models 7 days ago

primitive-ai/K2-Horizon-MoVA-36B-A4B-mixed-NVFP4-FP8

Text Generation • 33B • Updated 7 days ago • 910 • 1

primitive-ai/K2-Horizon-MoVA-36B-A4B-NVFP4

Text Generation • 37B • Updated 7 days ago • 2.08k

updated a model 8 days ago

primitive-ai/DeepSeek-V4-Flash-Vision-Exp-REAP-145B

Text Generation • 146B • Updated 8 days ago • 1.05k • 7

New activity in primitive-ai/Qwen3.8-Flash-Next-mixed-NVFP4-FP8 8 days ago

Benchmarked this checkpoint + PLE INT4 overlay on 1× RTX PRO 6000 Blackwell (96 GB) + 64 GB host RAM — vs ExLlamaV3 and vs Qwen3.8-27B

6

#3 opened 8 days ago by

Marzero

published a model 8 days ago

primitive-ai/K2-Horizon-MoVA-36B-A4B-mixed-NVFP4-FP8

Text Generation • 33B • Updated 7 days ago • 910 • 1

updated 3 models 8 days ago

primitive-ai/Qwen3.8-Flash-Next-PLE-quant

Updated 8 days ago • 4

primitive-ai/Qwen3.8-Flash-Next-mixed-NVFP4-FP8

Image-Text-to-Text • 120B • Updated 8 days ago • 5.74k • 18

primitive-ai/Qwen3.8-Flash-Next-NVFP4

Image-Text-to-Text • 120B • Updated 8 days ago • 16.1k • 19

published a model 10 days ago

primitive-ai/K2-Horizon-MoVA-36B-A4B-NVFP4

Text Generation • 37B • Updated 7 days ago • 2.08k

New activity in primitive-ai/Qwen3.8-Flash-Next-mixed-NVFP4-FP8 10 days ago

Error when using --moe-backend marlin per the 09-03 suggestion

1

#2 opened 10 days ago by

timbuksu

published a model 11 days ago

primitive-ai/granite-4.2-30b-mixed-NVFP4-FP8

Text Generation • 16B • Updated 11 days ago • 49

updated a model 11 days ago

primitive-ai/granite-4.2-30b-mixed-NVFP4-FP8

Text Generation • 16B • Updated 11 days ago • 49