Tevunah.ai

TevunahAi's activity

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

rockylynnstein 

updated a Space 27 days ago

Configuration error

README

🚀

rockylynnstein 

updated a model 28 days ago

TevunahAi/Grok-1-BF16

316B • Updated 28 days ago • 51

rockylynnstein 

published a model about 1 month ago

TevunahAi/Grok-1-BF16

316B • Updated 28 days ago • 51

rockylynnstein 

updated a collection about 1 month 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

rockylynnstein 

updated a model about 1 month ago

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

27B • Updated Mar 28 • 392

rockylynnstein 

published a model about 1 month ago

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

27B • Updated Mar 28 • 392

rockylynnstein 

updated a collection about 1 month 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

rockylynnstein 

updated a model about 1 month ago

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

9B • Updated Mar 28 • 87 • 1

rockylynnstein 

published a model about 1 month ago

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

9B • Updated Mar 28 • 87 • 1

rockylynnstein 

updated a model about 1 month ago

TevunahAi/grok-2-FP8

Text Generation • 270B • Updated Mar 27 • 21 • 2

rockylynnstein 

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

SGLang Deployment Compatibility for Agentic Workloads

1

#1 opened 4 months ago by

yalmasri

Add mlx conversion

1

#2 opened 3 months ago by

alejandroblancorevolut

rockylynnstein 

updated a collection 4 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

rockylynnstein 

updated a model 4 months ago

TevunahAi/CodeLlama-34B-TevunahAi-GPTQ

46B • Updated Jan 10 • 8

rockylynnstein 

published a model 4 months ago

TevunahAi/CodeLlama-34B-TevunahAi-GPTQ

46B • Updated Jan 10 • 8

rockylynnstein 

updated a model 4 months ago

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

11B • Updated Jan 10 • 9

rockylynnstein 

updated a collection 4 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