My Local LLM Was Running at 1.6% of Its Context. Here's the Setting That Fixed It

A developer discovered that their local LLM was running at only 1.6% of its context capacity due to a default setting in LM Studio, which capped the context length at 4096 tokens despite the model supporting 262,144. After increasing the context length to 260,000, the model's performance on long-document tasks improved dramatically, highlighting the importance of checking context settings over blaming model weights.

I run a content pipeline on a Mac mini 48GB unified memory that splits long blog drafts into platform-specific short-form pieces. That job — read a 30-page document, hold the whole thing in mind, extract what matters for YouTube Shorts vs TikTok vs Reels — is exactly what long-context LLMs are supposed to be good at. Mine wasn't. It kept "forgetting" the second half of every document, dropping key details, and producing shallow summaries no matter how I tuned the prompt. I did what you'd do. Simplified the prompt. Rewrote the template. Swapped models. Re-downloaded them, twice. Spent entire evenings after work on this, convinced the model was the problem — a Q4 K M quantized 13B–20B model should handle long documents, right? The symptoms said otherwise: solid on the first pages, incoherent by the end. Classic context-window behavior. I just didn't see it yet. Then I actually read the LM Studio load log instead of scrolling past it: context length: 4096 The model I was running supports 262,144 tokens of context . It was loaded with 4,096 . That's 1.6% of what the model can do. A 48-lane highway restricted to one lane — and every long document I fed it was quietly getting truncated into memory of just the opening section. LM Studio's just-in-time model loading picks a conservative default context length on first load. For chat and short Q&A, 4096 is plenty and keeps memory pressure low — a sensible default for most users. For document-scale work, it's a silent killer. Nothing errors out. Nothing warns you. The model just appears to have a bad memory. Context is the model's working memory. Cap it at 4k tokens and a 30-page brief becomes "read the first two pages, forget the rest." Two things: Context Length: 260000 whatever your model supports — check the model card, not the default , then reload. On 48GB of unified memory the larger KV cache is entirely affordable.Immediate, dramatic improvement. Full-document comprehension, per-platform extraction without drift, details intact end to end. Same model, same hardware, same prompt — one setting was capping ~98% of the model's effective utility for my workload. Defaults are tuned for the average case, and document-scale synthesis is not the average case. When a local LLM "feels dumb," check what it was actually loaded with before blaming the weights: context length is actually in effect?The most expensive performance bug I've shipped was a single default value. This post is based on a first-hand work log, written with AI assistance.