Quants that run fast on single 3090/4090 card with 24GB of VRAM and 4096 context length
TeeZee
TeeZee
AI & ML interests
LLM Roleplaying, on a quest to create a perfect model
Recent Activity
updated
a model
about 2 hours ago
TeeZee/QwQ-32B-bpw8.0-h8-exl2
published
a model
about 5 hours ago
TeeZee/QwQ-32B-bpw8.0-h8-exl2
updated
a model
about 14 hours ago
TeeZee/QwQ-32B-abliterated-bpw4.0-h8-exl2
Organizations
None yet
Collections
12
models
106
TeeZee/QwQ-32B-bpw8.0-h8-exl2
Text Generation
•
Updated
TeeZee/QwQ-32B-abliterated-bpw4.0-h8-exl2
Text Generation
•
Updated
TeeZee/DeepSeek-R1-Distill-Qwen-32B-bpw4.0-h8-exl2
Text Generation
•
Updated
TeeZee/QwQ-32B-bpw4.0-h8-exl2
Text Generation
•
Updated
TeeZee/DeepHermes-3-Mistral-24B-Preview-bpw4.0-h8-exl2
Text Generation
•
Updated
•
3
•
1
TeeZee/DeepHermes-3-Mistral-24B-Preview-bpw8.0-h8-exl2
Text Generation
•
Updated
TeeZee/Buttocks-7B-v2.1
Text Generation
•
Updated
•
63
•
1
TeeZee/Lumimaid-v0.2-8B-4bit-128g-autoround-autogptq-marlin
Updated
•
37
TeeZee/Lumimaid-v0.2-8B-4bit-128g-autoround-autogptq
Updated
•
7
TeeZee/Lumimaid-v0.2-8B-4bit-64g-hqq
Updated
•
15