Topic
Llama CPP
11 posts on llama cpp — guides and lab notes from real runs on hardware we own. New posts land here automatically. Start anywhere, or grab the copy-paste prompts that ship with them.
- 5 min read
Will That Local Model Fit? Do the VRAM Math First
A local LLM needs about half a gigabyte of VRAM per billion parameters at Q4, then KV cache and context stack on top. Here is how to know a model fits before you download 40 GB.
- 5 min read
How to Run Local LLM Verifier Loops on Owned Hardware
A local LLM workflow needs more than a model prompt. It needs a verifier loop that proves the file, command, URL, or report changed before the agent claims done.
- 5 min read
Tune llama.cpp --n-gpu-layers: VRAM Math & OOM Fixes (2026)
Set --n-gpu-layers too high and you OOM; too low and inference crawls. The VRAM math, KV-cache sizing, and a fast tuning loop to find the right value for your GPU. (2026)
- 5 min read
GGUF Quantization and VRAM: How to Pick Q4, Q5, or Q8 for Your GPU (2026)
VRAM decides your GGUF quant, not vibes. How I assign Q4, Q5, Q8 across an 8GB 3070, 16GB 5070 Ti, and 32GB 5090.
- 7 min read
llama.cpp Multi-GPU: Splitting a Model Across Cards with --tensor-split
Split a 70B model across multiple GPUs with llama.cpp. How --tensor-split, --main-gpu, and --split-mode work on a real consumer rig.
- 6 min read
How to Tune --n-gpu-layers for Your VRAM Budget
How to actually pick --n-gpu-layers: the offload math, finding the number with nvidia-smi, multi-GPU splits, and the top OOM mistakes.
- 6 min read
How to Pick a GGUF Quant Level for Your VRAM Budget
Given your GPU, which GGUF quant do you actually pick? The VRAM math, a card-by-card table, and the quality tradeoff in plain terms.
- 6 min read
llama.cpp -ngl 99 Still on CPU? 5 Fixes, Ranked (2026)
You set -ngl 99 and llama.cpp still pins the CPU — the flag isn't the bug. Here's the 30-second load-log check and the 5 real causes, ranked by how often they bite.
- 8 min read
GGUF Quantization 2026: Q4_K_M vs Q5 vs Q8 — Which to Pick
Short answer: Q4_K_M wins for most local LLMs — 75% smaller with near-zero quality loss. Q5, Q6 and Q8 each win edge cases. Benchmarked on real GPUs — here's the pick for your VRAM. (2026)
- 7 min read
llama.cpp n-gpu-layers Explained: -1 vs 0 + VRAM Guide (2026)
Setting --n-gpu-layers wrong tanks your tokens/sec or crashes with OOM. Here's exactly what to use (-1, 0, or a number), the VRAM-per-layer math, and 4060-4090 benchmarks.
- 7 min read
Local LLM on Consumer GPUs: 50 req/s, $0/Call [Benchmarks 2026]
Cloud LLM bills hit $2K/month fast. An RTX 5070 Ti serves Llama 3.1 at 50 req/s for $0 per call — we benchmarked 4 consumer GPUs and built the exact production setup.
The AI agent build notes
Real costs, real tools, no fluff. M-F when I ship, publish, or learn something worth sending.