Large models quantized with 4 datasets at smaller sized due to sized of model, but still above average for better results.
AI & ML interests
None defined yet.
Recent Activity
View all activity
These models are quantized in mixed precision that allows them to have a smaller footprint than fp8, but still high quality.
-
TevunahAi/granite-34b-code-instruct-8k-Ultra-Hybrid
Text Generation • 11B • Updated • 1 -
TevunahAi/Llama-3.1-70B-Instruct-Ultra-Hybrid
Text Generation • 22B • Updated -
TevunahAi/Qwen3-30B-A3B-Instruct-UltraHybrid-GPTQ-v2
31B • Updated • 18 -
TevunahAi/Nemotron-3-Nano-30B-A3B-GPTQ
Text Generation • 6B • Updated • 4.72k • 2
Models quantized in the FP8 format that used 4 high quality datasets.
-
TevunahAi/Apertus-70B-Instruct-2509-2048-Calibration-FP8
Text Generation • 71B • Updated • 5 -
TevunahAi/granite-20b-code-instruct-8k-2048-Calibration-FP8
Text Generation • 20B • Updated • 1 -
TevunahAi/Granite-34B-Code-Instruct-8k-2048-Calibration-FP8
Text Generation • 34B • Updated • 6 -
TevunahAi/gpt-oss-20b-2048-Calibration-FP8
Text Generation • 21B • Updated • 275 • 1
Large models quantized with 4 datasets at smaller sized due to sized of model, but still above average for better results.
These models are quantized in mixed precision that allows them to have a smaller footprint than fp8, but still high quality.
-
TevunahAi/granite-34b-code-instruct-8k-Ultra-Hybrid
Text Generation • 11B • Updated • 1 -
TevunahAi/Llama-3.1-70B-Instruct-Ultra-Hybrid
Text Generation • 22B • Updated -
TevunahAi/Qwen3-30B-A3B-Instruct-UltraHybrid-GPTQ-v2
31B • Updated • 18 -
TevunahAi/Nemotron-3-Nano-30B-A3B-GPTQ
Text Generation • 6B • Updated • 4.72k • 2
These models have been quantized in FP8 format.
Models quantized in the FP8 format that used 4 high quality datasets.
-
TevunahAi/Apertus-70B-Instruct-2509-2048-Calibration-FP8
Text Generation • 71B • Updated • 5 -
TevunahAi/granite-20b-code-instruct-8k-2048-Calibration-FP8
Text Generation • 20B • Updated • 1 -
TevunahAi/Granite-34B-Code-Instruct-8k-2048-Calibration-FP8
Text Generation • 34B • Updated • 6 -
TevunahAi/gpt-oss-20b-2048-Calibration-FP8
Text Generation • 21B • Updated • 275 • 1