Rocky Lynn Stein PRO

rockylynnstein's activity

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

updated a Space about 4 hours ago

Configuration error

README

🚀

updated a collection about 21 hours ago

Chochmah

Collection

These models are the first coded from scratch TevunahAi models. This is in its infancy, but we have plans to push forward into the future. • 1 item • Updated about 21 hours ago

updated a model about 21 hours ago

TevunahAi/chochmah-350m

Text Generation • 0.4B • Updated about 21 hours ago • 319

published a model about 21 hours ago

TevunahAi/chochmah-350m

Text Generation • 0.4B • Updated about 21 hours ago • 319

updated a model 5 months ago

TevunahAi/Grok-1-BF16

316B • Updated Mar 31 • 28

published a model 5 months ago

TevunahAi/Grok-1-BF16

316B • Updated Mar 31 • 28

updated a collection 5 months ago

Ultra Quantization Hybrid Model.

Collection

These models are quantized in mixed precision that allows them to have a smaller footprint than fp8, but still high quality. • 15 items • Updated Mar 28 • 1

updated a model 5 months ago

TevunahAi/Qwen3.5-27B-TevunahAi-GPTQ

27B • Updated Mar 28 • 10

published a model 5 months ago

TevunahAi/Qwen3.5-27B-TevunahAi-GPTQ

27B • Updated Mar 28 • 10

updated a collection 5 months ago

Ultra Quantization Hybrid Model.

Collection

These models are quantized in mixed precision that allows them to have a smaller footprint than fp8, but still high quality. • 15 items • Updated Mar 28 • 1

updated a model 5 months ago

TevunahAi/Qwen3.5-9B-TevunahAi-GPTQ

9B • Updated Mar 28 • 12 • 1

published a model 5 months ago

TevunahAi/Qwen3.5-9B-TevunahAi-GPTQ

9B • Updated Mar 28 • 12 • 1

updated a model 5 months ago

TevunahAi/grok-2-FP8

Text Generation • 270B • Updated Mar 27 • 16 • 3

New activity in TevunahAi/Nemotron-3-Nano-30B-A3B-GPTQ 7 months ago

SGLang Deployment Compatibility for Agentic Workloads

1

#1 opened 8 months ago by

yalmasri

Add mlx conversion

1

#2 opened 7 months ago by

alejandroblancorevolut

updated a collection 7 months ago

Ultra Quantization Hybrid Model.

Collection

These models are quantized in mixed precision that allows them to have a smaller footprint than fp8, but still high quality. • 15 items • Updated Mar 28 • 1

updated a model 7 months ago

TevunahAi/CodeLlama-34B-TevunahAi-GPTQ

46B • Updated Jan 10 • 7

published a model 8 months ago

TevunahAi/CodeLlama-34B-TevunahAi-GPTQ

46B • Updated Jan 10 • 7

updated a model 8 months ago

TevunahAi/Llama-3.1-8B-Instruct-TevunahAi-GPTQ

11B • Updated Jan 10 • 11