SmolLM2-135M-Q4_K_M-QLora-30 : GGUF

• For text only LLMs: llama-cli -hf maddoxreed/SmolLM2-135M-Q4_K_M-QLora-30 --jinja
• For multimodal models: llama-mtmd-cli -hf maddoxreed/SmolLM2-135M-Q4_K_M-QLora-30 --jinja

Available Model files:

• SmolLM2-135M.Q4_K_M.gguf This was trained 2x faster with Unsloth