unsloth/Qwen-Image-Edit-2511-GGUF
Image-to-Image • 20B • Updated • 109k • 433
[models] RTX a6000 48gb
Models that run well on a *standalone* RTX a6000's 48gb of VRAM.
-
-
unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF
24B • Updated • 34.4k • 127 -
zai-org/GLM-Image
Text-to-Image • Updated • 3.89k • • 1.04k -
nvidia/personaplex-7b-v1
Audio-to-Audio • Updated • 482k • 2.43k
diffusers/FLUX.2-dev-bnb-4bit
Image-to-Image • Updated • 23k • 29Note fantastic on a single A6000, low res, high steps, use it to make upscale candidates quickly
-
unsloth/GLM-4.7-Flash-GGUF
Text Generation • 30B • Updated • 129k • 600 -
noctrex/SERA-32B-GGUF
Text Generation • 33B • Updated • 61 • 4 -
unsloth/GLM-4.7-Flash-REAP-23B-A3B-GGUF
Text Generation • 23B • Updated • 18k • 190 -
bartowski/ServiceNow-AI_Apriel-1.6-15b-Thinker-GGUF
Image-Text-to-Text • 14B • Updated • 1.72k • 28 -
Qwen/Qwen3-Coder-Next
Text Generation • 80B • Updated • 679k • • 1.26k -
LiquidAI/LFM2-24B-A2B-GGUF
Text Generation • 24B • Updated • 55.7k • 121 -
unsloth/Qwen3.5-35B-A3B-GGUF
Image-Text-to-Text • 35B • Updated • 1.31M • 806 -
unsloth/gemma-4-31B-it-GGUF
Image-Text-to-Text • 31B • Updated • 1.18M • 304 -
fishaudio/s2-pro
Text-to-Speech • 5B • Updated • 50.8k • 838