qwen3.8-27b-pruned-enru-GGUF
27-миллиардная Qwen, у которой вырезан «лишний» кусок словаря, и две сборки квантования: IQ3XXS — целиком в 12 ГБ...
27-миллиардная Qwen, у которой вырезан «лишний» кусок словаря, и две сборки квантования: IQ3XXS — целиком в 12 ГБ...
Русско-английская, кодоориентированная Gemma-4-E4B, у которой вырезан «лишний» кусок словаря. Не дистилляция, не файнтюн, не abliteration — веса модели...
FIT-GGUF v0.5.1ALL FIVE TIERS GATE-VERIFIED5 FIT + BF16 + IMATRIXMTP · VISION + VIDEOMEASURED KL + SAME-TOPAPACHE-2.0 Sage-A1.5-abliterated...
All APEX-I quantizations are independently computed on private cloud clusters funded 100% out-of-pocket. If this release helps your...
Quantization test results for K2-Horizon-7B (dense) and LFM2.5-8B-A1B (MoE), comparing standard llama.cpp quantization against a fork that adds...
Two GGUF builds of a mechanically converted sparse-MoE version of Qwen3.8-27B. The dense SwiGLU feed-forward networks were re-partitioned...
Spark-X2.5-4B is a compact general-purpose model for conversation, writing, translation, reasoning, coding and tool use with a hybrid...
Independently computed using dedicated cloud compute clusters, funded 100% out-of-pocket. If you consider these releases to be of...
> TL;DR: VibeThinker-3B at 1.16 GB (3-bit) or 1.35 GB (3.5-bit), compared with 6.18 GB in BF16. >...
Mixed-precision GGUF quantizations of Jiunsong/SuperDeepseek-V4-Flash-abliterated, an abliterated derivative of DeepSeek V4 Flash 0731. > These files contain IK-specific...