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-Base-InstructMidm-2.0-Mini-InstructQwen3.5-0.8B-text-onlyQwen3.5-9B-text-onlyQwen3.5-4B-text-onlyko-gemma-2-9b-it-GGUF-quantizationscope-guard-4B-q-2601claim-extractor-4B-q-2605Qwen3.5-2B-text-onlyDeepSeek-v4-FableALLaM-7B-Instruct-preview-Q4_K_M-GGUFtelecom-intelligence-model-v7-GGUFscope-guard-v2-4B-q-2609telecom-intelligence-model-v7-mergedllm-jp-4-kappa-32b-a3b-v0.1claim-extractor-2B-q-2605HACHI-Summary-Ja-sarashina2.2-0.5b-instruct-v0.1precis-ggufintelligence-cod-rag-7b-v3ATLAS-8B-InstructArabic-llama3.1-16bit-FTtelecom-intelligence-model-v3-mergedtelecom-intelligence-model-v6-mergedIntelligence-R1-Distill-7Bal-baka-llama3-8b-experimentaltsukuyomichan-omnivoice-compressedIntelligence-7COMPASS_Qwen2.5-7B-Instruct_LoRAal-baka-4bit-llama3-8bATLAS-8B-Thinking