barozp/Qwen3.8-27B-Opus-Distill-GGUF
Model card: source chain as full-family bullet list
Upload README.md with huggingface_hub
Upload README.md with huggingface_hub
Fix mmproj filename, exact quant sizes, imatrix note (IQ quants now use imatrix, not without it)
Upload Qwen3.8-27B-Opus-Distill-IQ1_M.gguf with huggingface_hub
Upload Qwen3.8-27B-Opus-Distill-IQ2_XXS.gguf with huggingface_hub
Upload Qwen3.8-27B-Opus-Distill-IQ3_XXS.gguf with huggingface_hub
Add imatrix.dat for requantization (Qwen3.8-27B family, 512 samples of opus-reasoning-distill-train)
Upload Qwen3.8-27B-Opus-Distill-mmproj-f16.gguf with huggingface_hub
Upload Qwen3.8-27B-Opus-Distill-Q3_K_M.gguf with huggingface_hub
Upload Qwen3.8-27B-Opus-Distill-Q4_K_M.gguf with huggingface_hub
Upload Qwen3.8-27B-Opus-Distill-Q5_K_M.gguf with huggingface_hub
Upload Qwen3.8-27B-Opus-Distill-Q6_K.gguf with huggingface_hub
Upload Qwen3.8-27B-Opus-Distill-Q8_0.gguf with huggingface_hub
Update model card: full detailed card (benchmarks, quant ladder, mmproj, MTP)
Upload Qwen3.8-27B-Opus-Distill-BF16.gguf with huggingface_hub
Update README.md
Add base_model / base_model_relation: quantized (model tree)
Add placeholder card, pending Qwen3.8-27B release
initial commit