The LiquidAI/LFM2-24B-A2B galaxy

51 models are built on LiquidAI/LFM2-24B-A2B: 35 quantized, 12 fine-tuned, 4 adapters and 0 merges. Together they were downloaded 346,446 times in the last 30 days.

Most downloaded direct derivatives

lmstudio-community/LFM2-24B-A2B-MLX-4bit (quantized), 78.7K downloads in 30 days
lmstudio-community/LFM2-24B-A2B-MLX-5bit (quantized), 77.7K downloads in 30 days
lmstudio-community/LFM2-24B-A2B-MLX-8bit (quantized), 77.7K downloads in 30 days
lmstudio-community/LFM2-24B-A2B-MLX-6bit (quantized), 77.5K downloads in 30 days
LiquidAI/LFM2-24B-A2B-GGUF (quantized), 12K downloads in 30 days
bartowski/LiquidAI_LFM2-24B-A2B-GGUF (quantized), 3.1K downloads in 30 days
mudler/LFM2-24B-A2B-APEX-GGUF (quantized), 1.5K downloads in 30 days
mradermacher/LFM2-24B-A2B-i1-GGUF (quantized), 990 downloads in 30 days
mradermacher/LFM2-24B-A2B-GGUF (quantized), 538 downloads in 30 days
cyankiwi/LFM2-24B-A2B-AWQ-4bit (quantized), 507 downloads in 30 days
LiquidAI/LFM2-24B-A2B-MLX-4bit (quantized), 386 downloads in 30 days
MaziyarPanahi/LFM2-24B-A2B-GGUF (quantized), 324 downloads in 30 days
noctrex/LFM2-24B-A2B-MXFP4_MOE-GGUF (quantized), 310 downloads in 30 days
mlx-community/LFM2-24B-A2B-4bit (quantized), 309 downloads in 30 days
LiquidAI/LFM2-24B-A2B-MLX-8bit (quantized), 269 downloads in 30 days
LiquidAI/LFM2-24B-A2B-MLX-bf16 (finetune), 204 downloads in 30 days
huihui-ai/Huihui-LFM2-24B-A2B-abliterated (finetune), 191 downloads in 30 days
kingjones777/LFM2-24B-A2B-ROCmFPX-GGUF (quantized), 186 downloads in 30 days
LiquidAI/LFM2-24B-A2B-MLX-5bit (quantized), 185 downloads in 30 days
LiquidAI/LFM2-24B-A2B-MLX-6bit (quantized), 180 downloads in 30 days
LiquidAI/LFM2-24B-A2B-ONNX (quantized), 175 downloads in 30 days
DevQuasar/LiquidAI.LFM2-24B-A2B-GGUF (quantized), 109 downloads in 30 days
paperscarecrow/LFM2-24B-A2B-Abliterated (quantized), 91 downloads in 30 days
OpenVINO/LFM2-24B-A2B-int4-ov (finetune), 78 downloads in 30 days
farbodtavakkoli/OTel-LLM-24B-IT (finetune), 73 downloads in 30 days