Qwen3.8_1.2B_LFM_Distillation_GGUF : GGUF

• For text only LLMs: llama-cli -hf Ma7ee7/Qwen3.8_1.2B_LFM_Distillation_GGUF --jinja
• For multimodal models: llama-mtmd-cli -hf Ma7ee7/Qwen3.8_1.2B_LFM_Distillation_GGUF --jinja

Available Model files:

• LFM2.5-1.2B-Thinking.Q8_0.gguf
• LFM2.5-1.2B-Thinking.Q5_K_M.gguf
• LFM2.5-1.2B-Thinking.Q4_K_M.gguf This was trained 2x faster with Unsloth