CodingGenesis archive2026-09
Coding on an 8GB 5060, where tuning the GPU/CPU split matters more than tok/sA daily local coder on an RTX 5060 8GB and 32GB of RAM finds responsiveness under memory pressure matters more than benchmark speed.
Capacity range
Exact reported VRAM
Practice
Model
Quantization
Context length
Reported speed
Runtime
Tools / workflow (harness)
Record origin
EXPLORE BY CAPACITY
Start with your machine.
Capacity is the reported total for this setup. Multi-GPU and unified-memory layouts can behave differently.
8 GB or lessLaptops, iGPUs and modest cards9–12 GBEntry-level local inference13–16 GBCurrent mid-range cards17–20 GBRX 7900 XT and compact pro cards21–24 GB3090, 4090 and 7900 XTX class25–32 GB5090 and workstation cards33–48 GBWorkstation and multi-GPU setups49–96 GBLarge multi-GPU and datacenter setups97 GB+Unified memory, servers and clusters
3 resultsEvery record keeps its origin visible.
CodingGenesis archive2026-09
Fitting Qwen 27B and a 96K context onto a single 3090A 3090 owner runs Qwen 3.8 27B daily in Cline at a 96K context by quantising the KV cache to q8_0, reporting about 43 tok/s once the model stops thinking.
Business automationGenesis archive2026-09
A 2B local model behind 30+ private capabilitiesA small GPU runs sub-10B models through Ollama, with a custom skill and memory layer driving a broad set of offline personal and automation workflows.