A purpose-built engine (NInfer 4080) runs ISTA-DASLab's Qwen 3.8 27B GSQ at 100K+ context on one RTX 4080 16GB, measuring up to ~2,720 tok/s prefill and ~262 tok/s decode through DFlash2 speculative decoding.
Start with your machine.
Capacity is the reported total for this setup. Multi-GPU and unified-memory layouts can behave differently.
A purpose-built engine (NInfer v1.3) fits Qwen 3.8 27B at a real 131,072-token context and KV capacity, plus vision, on one RTX 5080 16GB, qualifying ~71.6 tok/s decode and ~1,381 tok/s prefill on a 118,001-token prompt.
Three GPUs spread across machines run Qwen 3.8 27B through a custom stateful agent layer to build a personal finance and portfolio tracker without shipping documents to the cloud.
A small but clear split: the frontier model plans and verifies, while Qwen 3.8 runs on nInfer as the fast local coder, saving tokens.