-
qwen3.8-27B_GSQ_RCO
Dynamically quantized only 12GB MTP model with precision close to the base model picked from hugging face ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-IQ3_S-GGUF, highly efficient model
vision3,006 Pulls 1 Tag Updated 1 month ago
-
Qwen3.8-27B-UD-Q4_K_M
Qwen3.8-27B-UD-Q4_K_M with fixed template for claude code
vision510 Pulls 1 Tag Updated 1 month ago
-
Qwen3.8-27B-pi-mtp
Optimized Qwen3.8 for pi coding harness with mtp weights from https://huggingface.co/bytkim/Qwen3.8-27B-pi-GGUF
vision91 Pulls 1 Tag Updated 1 month ago