# b11626: model: split layers evenly when no device reports free memory (#29677)

> **Key Architectural Takeaway:** When every device reports zero free memory the split points are normalized by a zero sum, the NaN split sends layers to a device index past the end and loading aborts with vector::_M_range_check.

**Published:** 2026-10-14T06:30:00+00:00 
**Source:** Llama.cpp Tensor Acceleration 
**Category:** ai-local-edge 
**Canonical URL:** https://fosswire.org/news/b11626-model-split-layers-evenly-when-no-device-reports-free.html 

## Executive Summary
When every device reports zero free memory the split points are normalized by a zero sum, the NaN split sends layers to a device index past the end and loading aborts with vector::_M_range_check.

## Architectural & Systems Analysis
From an artificial intelligence architecture, model weights governance, and inference efficiency perspective:

- **Weights Accessibility & Sovereignty:** Evaluates whether weights are open for private self-hosting or locked behind centralized cloud APIs.
- **Quantization & Edge Performance:** Kernel optimizations (4-bit/8-bit GGUF, AWQ, EXL2) allow high tokens-per-second on consumer GPUs and Apple Silicon.
- **Reasoning & Architectural Scaling:** Scrutinizes mixture-of-experts (MoE), attention mechanisms, and fine-tuning datasets against open community benchmarks.

## Impact on the Open Ecosystem
Protects developers and enterprises from proprietary black-box entrapment, fostering auditable, sovereign AI infrastructure.