LLMs on Consumer Hardware — Part 1: The Stack and First Benchmarks

A developer documented a local LLM project running models on consumer hardware, benchmarking Gemma 4 26B against smaller models. The primary desktop with an AMD RX 6900XT achieved 18.86 tokens/sec on Gemma 4 26B, which scored 50/50 on a five-task quality suite, leading to its adoption as the primary model despite slower throughput.

This is the first in a series of build-log posts documenting a local LLM project, in which models are run on owned consumer hardware rather than through a cloud API. The present entry covers the hardware, the software stack, and the benchmarks by which a primary model was selected. Two machines are used, both consumer-grade. All benchmarks reported below were obtained on the primary desktop. | Machine | CPU | RAM | GPU | |---|---|---|---| Primary desktop | Ryzen 5950X | ~80 GB DDR4 | AMD RX 6900XT 16 GB | Secondary box | Ryzen 5600G | 32 GB | NVIDIA GTX 1060 6 GB | Ollama serves as the model runner across two GPU vendors: ROCm 5.7 for the AMD card on the primary desktop, and CUDA for the NVIDIA card on the secondary box. The primary model is Gemma 4 26B, a mixture-of-experts model with roughly 3.8B active parameters, quantized to Q4 K M and occupying approximately 18 GB on disk. On the RX 6900XT it is run with an automatic GPU/CPU layer split, as the Q4 weights together with the KV cache exceed the 16 GB of available VRAM. Several Ollama settings were enabled to recover headroom: flash attention, and an 8-bit q8 0 KV cache, the latter approximately halving the cache footprint. A free cloud tier is retained for occasional heavier tasks, though the objective is to run as much as possible locally. Before a primary model was chosen, the installed models were benchmarked. Two properties were of interest: throughput and output quality. Throughput was measured on the primary desktop with a 500-word essay prompt ollama run <model --verbose : | Model | Tokens/sec | Duration | Tokens out | |---|---|---|---| | gemma4:26b | 18.86 | 50.11s | 945 | | gemma4-26b 64K ctx | 17.96 | 51.99s | 934 | | mistral:7b-instruct | 34.81 | 10.17s | 354 | | llama3.2 | 57.11 | 3.99s | 228 | The smaller models are substantially faster; their token counts, however, are lower, and in practice their responses were correspondingly shallower. Quality was assessed with a five-task suite spanning logic, coding, summarization, creative writing, and instruction-following: | Model | Score | Note | |---|---|---| | gemma4-26b 64K | 50/50 | Flawless instruction-following | | glm-4.7-flash | 42/50 | Missed only a complex string-formatting task | | qwen3-coder:30b | 40/50 | Overthinks logic; hallucinated a fake country | | llama3.2 | 28/50 | Failed logic entirely | | mistral:7b | 26/50 | Failed logic and negative constraints | A harder ten-task variant — incorporating a lipogram, a theory-of-mind question, and a riddle — was subsequently administered, on which Gemma 4 26B scored 99/100 while sustaining approximately 17 tokens/sec. This represents the local optimum: strong quality at a workable speed. The principle that follows is that throughput and quality trade off against one another, and the fastest available model is rarely the appropriate default for substantive work. Gemma 4 26B is slower than the 7B models yet markedly more accurate, and it was therefore adopted as the primary model. With a runner, a model, and a hardware baseline established, subsequent entries turn to the extraction of useful work from the setup. We intend to address context length and KV-cache trade-offs; the distinction between prefill and generation, and why a machine without a GPU can sustain conversation yet falter on large prompts; and the practice of keeping models resident to avoid cold-start reload penalties. The measured figures are reported as-is, dead ends included. Part 2 will follow.