Multimodal Large Language Models (MLLMs) are increasingly used for dietary assessment from meal images, where retrieval-augmented grounding was shown to sharpen nutrition estimates. However, we find this premise no longer holds for current MLLMs. A modern MLLM's direct estimate now matches or surpasses the full retrieval pipeline. This raises a question: if retrieval no longer improves the overall estimate, can it still deliver the two things clinicians value, accurate portions and a traceable, item-by-item record? We pursue this while preserving what matters for clinical adoption: minimal user burden (a single, unannotated meal image), explainability (an auditable record), and privacy (locally hosted inference). We introduce Open-KNEAD, a knowledge-grounded agentic framework for meal nutrition estimation that is training-free and locally deployable. Each decomposed food item is grounded to a Food and Nutrient Database for Dietary Studies (FNDDS) code via selective, nutrient-aware retrieval, composing an auditable per-item record. Across two open MLLM families and three cuisines, Open-KNEAD improves portion estimates over both prior grounding methods and direct estimation in most backbone-dataset settings. An agent-internal recipe-prior step further recovers the invisible cooking-added energy that biases estimates on non-US cuisine. The advantage is largest on the dietitian-verified ACETADA dataset, where the local open agent surpasses the direct portion estimates of two frontier closed models by roughly $30\%$ and $53\%$, all while keeping every meal image on local hardware. We release the Open-KNEAD framework and its agent-ready FNDDS knowledge base.
Sparse Mixture-of-Experts (MoE) language models separate total parameter count from per-token active computation, but local inference systems often still require the full model, key-value cache, runtime buffers, and operatingsystem headroom to fit in fast memory. MawForge tests a different systems hypothesis: local MoE serving can be made practical on constrained unified-memory machines by storing the full model on disk, keeping common tensors resident, and materializing routed expert tensors into a bounded execution cache on demand. The central finding is that MawForge is effective as a bounded execution mechanism and measurement substrate for local MoE inference, but not as a cache-maximization policy. Performance depends on balancing expert reuse against resident footprint, KV-cache size, quantization, route locality, and macOS memory pressure.
The local deployment of large language models (LLMs) is gaining traction due to privacy concerns and the desire for on-premise inference. However, the energy costs on consumer hardware remain poorly characterized, as most benchmarks focus solely on accuracy. This paper presents a reproducible, hardware-level energy benchmark of nine open-source LLMs (1B to 7B parameters) executed on a single consumer GPU (RTX 4060Ti 16GB). Using the Ollama inference engine, GPU power draw was sampled at 2Hz via nvidia-smi across a fixed prompt set. We evaluate mean/peak power, total energy per prompt (J/prompt), energy per output token (J/token), and throughput (tok/s). Our findings suggest that factors beyond raw parameter count, including model architecture and quantization strategy, drive energy efficiency. Specifically, gemma3:1b and llama3.2:1b achieve the lowest energy cost (0.56 J/token and 0.65 J/token) and the highest throughput (>170 tok/s). In contrast, the 7B-Mistral model consumes up to 4.4x more energy per token than the most efficient model. Notably, qwen3.5:2b exhibits anomalously high per-prompt energy due to extended internal reasoning, highlighting the need to distinguish between token generation modes in efficiency metrics.