models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
Midm-2.0-Mini-InstructMidm-2.0-Base-InstructRavenXAiLabs-Chaos-Agent-Qwen3.8-27B-Frontier-Intelligence-Injected-OBLITERATED-GGUFRavenXAiLabs-Chaos-Agent-Qwen3.8-27B-Frontier-Intelligence-Injected-OBLITERATED-MLXscope-guard-4B-q-2601DeepSeek-v4-FableQwen-14B-Chat-GGUF-Quantizationtelecom-intelligence-model-v7-mergedtelecom-intelligence-model-v7-GGUFALLaM-7B-Instruct-preview-Q4_K_M-GGUFQwen3.5-2B-OneCompression-4bit-MLXclaim-extractor-4B-q-2605Qwen3.6-40B-Grand-Intelligence-Fable-Fusion-Uncensored-Heretic-mxfp8claim-extractor-2B-q-2605LFM2-12B-A1B-SpeedDemon-High-Intelligence-Series-Bprecis-ggufllm-jp-4-kappa-32b-a3b-v0.1ATLAS-8B-ThinkingArabic-llama3.1-16bit-FTALLaM-7B-Instruct-preview-Q8_0-GGUFtelecom-intelligence-model-v6-mergedsentineltelecom-intelligence-model-v3-mergedal-baka-16bit-llama3-8bgemma2-9b-cpt-sealionv3-instruct-endpointal-baka-4bit-llama3-8bATLAS-8B-Instructsmolified-personalized-learning-content-intelligence-platformscope-guard-v2-4B-q-2609precis-merged-16bit