tinybrainbot-360m-a75m-v5.1-chat
A small chill-friend chatbot. This is the casual-conversation version of TinyBrainBot-360M-A75M-v5.1-Instruct: same 383M-parameter mixture-of-experts model (24 experts per...
A small chill-friend chatbot. This is the casual-conversation version of TinyBrainBot-360M-A75M-v5.1-Instruct: same 383M-parameter mixture-of-experts model (24 experts per...
One small model for chat, instructions, reasoning and math, now with line breaks and a name. A 383M-parameter...
DiffuSpace’s Clover-35B-A3B-Preview (a block-diffusion MoE tuned from Qwen3.6-35B-A3B, 3B active per token) quantized for Kapitsa, the Metal inference...
A 134.5 GiB mixed 2-bit GGUF of Reflection’s 501B MoE — all 256 experts retained — that runs...
> [!WARNING] > The files can change. This line of conversions is still being researched, > so any...
21.37 tok/s on one RTX 5090 32 GB with 128 GB RAM, using the recipe and patched llama.cpp...
GGUF files of Qwen2.5-1.5B-MoE-A0.9B, a Mixture-of-Experts conversion of Qwen2.5-1.5B with ~0.85B active parameters per token instead of 1.54B....
Редкая модель смеси экспертов, полученная из HuggingFaceTB/SmolLM2-360M. Каждый токен использует около 44% исходных вычислений MLP: 8 из 32...
Two GGUF builds of a mechanically converted sparse-MoE version of Qwen3.8-27B. The dense SwiGLU feed-forward networks were re-partitioned...
GRAFT-10B-A2B is a ~10B-parameter mixture-of-experts chat model from UltraLabs. Only about 2B parameters are active per token, so...