A collection of TurboQuant+ compressed models designed to improve quality at practical memory limits.
TurboQuant+ applies tensor-aware compression in
Tom Turney
thetom-ai
AI & ML interests
Building TurboQuant for fun
Organizations
models 18
thetom-ai/DeepSeek-V4-Flash-ConfigI-GGUF
Text Generation • 284B • Updated • 181 • 6
thetom-ai/DeepSeek-V4-Flash-ConfigI-MLX
Text Generation • 284B • Updated • 252 • 5
thetom-ai/Nemotron-TheHobbit-30B-A3B
Updated • 16 • 2
thetom-ai/Nemotron-H-8B-Base-8K-Config-I-GGUF
8B • Updated • 45
thetom-ai/PsyGuard-gpt-oss-20B-Orchestrator-alpha
Text Generation • 21B • Updated • 49
thetom-ai/PsyGuard-Gemma-4-26B-A4B-alpha
Text Generation • 25B • Updated • 47
thetom-ai/PsyGuard-Gemma-4-12B-alpha
Text Generation • 12B • Updated • 78
thetom-ai/PsyGuard-Qwopus-27B-alpha
Text Generation • 27B • Updated • 42 • 2
thetom-ai/MiniMax-M3-ConfigI-MLX
Text Generation • 427B • Updated • 94
thetom-ai/Spurgeon-Gemma-4-12B-v1
Text Generation • 12B • Updated • 57
datasets 0
None public yet