120-125B MoE Vision for 48-96 GB GPUs
Collection
Large MoE in EXL3 for 48-96 GB: Qwen3.8 Flash-Next (125B-A6B, MTP) and NVIDIA Nemotron-3.5-Super-VL (120B-A12B, vision, 1M ctx). vLLM Blackwell. • 4 items • Updated
Jorge Ramírez Espejo
JRamirez-UAB
AI & ML interests
Linux sysadmin at UAB (DCC).
Quantizing and testing local LLMs for a Spanish-language sysadmin agent (opencode + vLLM).
Recent Activity
updated a collection about 7 hours ago
120-125B MoE Vision for 48-96 GB GPUs published a model about 8 hours ago
JRamirez-UAB/Nemotron-3.5-Super-VL-120B-A12B-EXL3-2.25bpw-VL-48-96GB updated a model about 8 hours ago
JRamirez-UAB/Nemotron-3.5-Super-VL-120B-A12B-EXL3-2.25bpw-VL-48-96GBOrganizations
None yet
updated a
collection about 7 hours ago
published a
model about 8 hours ago
updated a
model about 8 hours ago
updated a
model 2 days ago
updated 11
models 3 days ago
JRamirez-UAB/Swift-1.5-Qwen3.8-Flash-Next-EXL3-3.75bpw-96GB
Image-Text-to-Text • 32B • Updated • 107
JRamirez-UAB/Qwen3.8-Flash-Next-EXL3-2.25bpw-48GB
Image-Text-to-Text • 20B • Updated • 137
JRamirez-UAB/Swift-1.5-Qwen3.8-Flash-Next-EXL3-2.25bpw-48GB
Image-Text-to-Text • 20B • Updated • 151
JRamirez-UAB/NeoHorse-1-9B-EXL3-16GB-12GB
Image-Text-to-Text • 4B • Updated • 165
JRamirez-UAB/Qwen3.8-27B-pi-EXL3-3.85bpw-24GB
Image-Text-to-Text • 8B • Updated • 190
JRamirez-UAB/Ornith-1.5-35B-A3B-EXL3-4.00bpw-24GB
Image-Text-to-Text • 10B • Updated • 224
JRamirez-UAB/Qwopus3.6-35B-A3B-Coder-EXL3-4.00bpw-24GB
Image-Text-to-Text • 10B • Updated • 213
JRamirez-UAB/Qwen3.6-35B-A3B-EXL3-4.00bpw-24GB
Image-Text-to-Text • 10B • Updated • 189
JRamirez-UAB/Ornith-1.5-9B-EXL3-16GB-12GB
Image-Text-to-Text • 4B • Updated • 245
JRamirez-UAB/Qwopus3.8-27B-Flash-V2-EXL3-3.85bpw-24GB
Image-Text-to-Text • 8B • Updated • 213
JRamirez-UAB/Qwen3.8-27B-EXL3-3.85bpw-24GB
Image-Text-to-Text • 8B • Updated • 236
updated 2
models 4 days ago
updated 3
collections 5 days ago