SparkLLM's Spark-X2.6-4B Runs Local Agents on 3.54 GB With Adjustable Reasoning
SparkLLM released Spark-X2.6-4B, a 4-billion-parameter Apache 2.0 model packaged as GGUF for local inference in Q4_K_M (3.54 GB) and Q8_0 (4.38 GB) builds for llama.cpp, Ollama and LM Studio, with the Hugging Face reposi…