lmcoleman/ThinkingCap-Qwen3.6-27B-ROCmFPX-GGUF
Upload README.md with huggingface_hub
Upload README.md with huggingface_hub
Upload README.md with huggingface_hub
Upload README.md with huggingface_hub
Upload README.md with huggingface_hub
Upload ThinkingCap-Qwen3.6-27B-ROCMFPX-MQ-Q6.gguf
Upload README.md with huggingface_hub
Remove mislabeled tier: size ratio places this file in a different band than its name claims (MagicQuant v1 band-collision defect)
Remove mislabeled tier: size ratio places this file in a different band than its name claims (MagicQuant v1 band-collision defect)
Add recommended-tier note (Q5 ties/beats Q6 within noise)
Card update: frontmatter: +pipeline_tag,quantized_by,language,base_model_relation
Name the known-good ROCmFPX fork commit these files were built with
Upload mmproj-ThinkingCap-Qwen3.6-27B-f16.gguf with huggingface_hub
Upload README.md with huggingface_hub
Upload ThinkingCap-Qwen3.6-27B-ROCMFPX-MQ-Q6.gguf with huggingface_hub
Upload ThinkingCap-Qwen3.6-27B-ROCMFPX-MQ-Q5.gguf with huggingface_hub
Upload ThinkingCap-Qwen3.6-27B-ROCMFPX-MQ-Q4.gguf with huggingface_hub
Upload README.md with huggingface_hub
initial commit