Calibrated quants for vLLM or llama cpp of Qwen models
Kyle Pearson PRO
pearsonkyle
AI & ML interests
Observational Astronomy, Exoplanets, Physical Modeling, Uncertainty Quantification
Recent Activity
liked a Space 1 day ago
kulkas2pintu/QWEN_EDIT_IMAGE updated a collection 3 days ago
Gemma4-Coder updated a model 3 days ago
pearsonkyle/gemma4-e4b-w4a16-mtp-vLLMOrganizations
None yet
models 14
pearsonkyle/gemma4-e4b-w4a16-mtp-vLLM
Text Generation • Updated
pearsonkyle/Qwen3.8-27B-GPTQ-W4A16
Image-Text-to-Text • 27B • Updated • 12.7k • 4
pearsonkyle/Qwen3.8-27B-imatrix-MTP-GGUF
Image-Text-to-Text • 27B • Updated • 5.03k • 9
pearsonkyle/tcg-frame-removal-klein4b
Image-to-Image • Updated • 43 •
pearsonkyle/gemma4-31b-imatrix-mtp-GGUF
Image-Text-to-Text • 31B • Updated • 1.49k • 3
pearsonkyle/Ornith-1.0-9B-imatrix-GGUF
Text Generation • 9B • Updated • 388 • 2
pearsonkyle/tmax-27b-imatrix-MTP-GGUF
Text Generation • 27B • Updated • 409 • 1
pearsonkyle/Qwopus3.6-27B-Coder-imatrix-MTP-GGUF
Text Generation • 27B • Updated • 369 • 6
pearsonkyle/DepthAnyPanorama-coreml
Depth Estimation • Updated • 5
pearsonkyle/Sharp-onnx
Image-to-3D • Updated • 3