JasonW2025/Qwen3.8-Flash-Next-NVFP4-Calibrated-KV
Image-Text-to-Text • 120B • Updated • 6
Jason Wong
JasonW2025
AI & ML interests
Gated models are basically sub-optimum and meant for testing only. They may not even run.
Recent Activity
updated a model 12 days ago
JasonW2025/Qwen3.8-Flash-Next-NVFP4-Calibrated-KV published a model 17 days ago
JasonW2025/Qwen3.8-Flash-Next-NVFP4-Calibrated-KV new activity about 1 month ago
JasonW2025/Qwen3.8-27B-NVFP4-W4A4:Restricted access to modelsOrganizations
None yet
models 21
JasonW2025/Qwen3.8-27B-NVFP4-W4A16
Image-Text-to-Text • 20B • Updated • 217
JasonW2025/Qwen3.8-27B-NVFP4-W4A4
Image-Text-to-Text • 20B • Updated • 310
JasonW2025/Ling-3.0-flash-HybridQuant-NVFP4-W4A16-LocalHessian
Text Generation • 66B • Updated • 517 • 4
JasonW2025/Ling-3.0-flash-HybridQuant-NVFP4-W4A16
Text Generation • 66B • Updated • 143
JasonW2025/Laguna-S-2.1-ModelOpt-NVFP4-W4A4-KVcal-vllm
Text Generation • 61B • Updated • 112 • 1
JasonW2025/Hy3-295B-A21B-HybridQuant-v1-vllm
Text Generation • 155B • Updated
JasonW2025/Laguna-S-2.1-ModelOpt-NVFP4-W4A16-vllm
Text Generation • 61B • Updated • 27
JasonW2025/Laguna-S-2.1-ModelOpt-NVFP4-W4A4-vllm
Text Generation • 61B • Updated • 3
JasonW2025/Qwen3.6-35B-A3B-HybridQuant-gptq-dv41-KVcal
20B • Updated • 12