TevunahAi/granite-34b-code-instruct-8k-Ultra-Hybrid
Text Generation
•
11B
•
Updated
•
5
Ultra Quantization Hybrid Model.
These models are quantized in mixed precision that allows them to have a smaller footprint than fp8, but still high quality.
-
-
TevunahAi/Llama-3.1-70B-Instruct-Ultra-Hybrid
Text Generation • 22B • Updated • 4 -
TevunahAi/Qwen3-30B-A3B-Instruct-UltraHybrid-GPTQ-v2
31B • Updated • 45 -
TevunahAi/Nemotron-3-Nano-30B-A3B-GPTQ
Text Generation • 6B • Updated • 1.6k • 2 -
TevunahAi/Granite-3.3-8B-Instruct-GPTQ
Text Generation • 8B • Updated • 8