Qwen3.8 27B Swift-1.5
on NVIDIA RTX 5060 Ti 16GB · llama.cpp · 81,920 ctx
Use cases
codingagentic
Summary
User reports about 40 tokens per second running a Swift-1.5 Qwen3.8 27B IQ3_S GGUF on an RTX 5060 Ti 16GB.
Setup is llama.cpp with MTP speculative decoding at 81920 context size, on a Ryzen 7 9800X3D with 32GB DDR5-6000.
User asks whether this is the best they can do for general use, coding and agentic tasks.