LFM2.5-24B-A2B-DERISKED-BF16
Standalone BF16 behaviorally modified derivative of Liquid AI’s LFM2.5-24B-A2B for reasoning, multilingual chat, and tool-enabled workflows. > Release...
Standalone BF16 behaviorally modified derivative of Liquid AI’s LFM2.5-24B-A2B for reasoning, multilingual chat, and tool-enabled workflows. > Release...
asinha08/slm-125m-base is a 125M parameter, Llama-compatible, decoder-only causal language model trained from scratch on a legal-first English corpus....
This model was converted to GGUF format from ZeroXClem/Qwen3.5-9B-Fable-5-Quad-Stock using llama.cpp (master) on Modal. Refer to the original...
ZeroXClem/Qwen3.5-9B-Fable-5-Quad-Stock is a four-way fusion of the most-downloaded Claude Fable 5 distills on the Qwen3.5-9B architecture, merged with...
manitcor/Qwen3.8-27B-Obliterated-E03 is a BF16, text-only derivative of Qwen/Qwen3.8-27B. It was produced with the experimental qwen38e03` refusal-direction intervention in...
Model collection | Technical report | Training code (coming soon) | Evaluation code NCP-ArchPreview is a latent-space autoregressive...
This repository contains a bfloat16 MLX conversion of empero-ai/Qwythos-9B-Claude-Mythos-5-1M for Apple Silicon inference with MLX, MLX-LM, MLX-VLM, and...
This is the BF16 model of DeekSeek V3-0324. Useful for quantization and inference on GPUs that do not...
This is an interesting merge of 14 cool models, created using mergekit. Enjoy exploring 🙂 This model was...
ZeroXClem/L3-Aspire-Heart-Matrix-8B — это экспериментальная языковая модель, созданная путем слияния трех высококачественных моделей параметров 8B с использованием метода слияния...