Qwen3.8 27B
on 2× NVIDIA RTX 3090 · llama.cpp · 200,000 ctx
Use cases
coding
Summary
User reports Qwen3.8-27B at 73 t/s on code and 58.5 t/s on prose on dual RTX 3090s (24 GB each, 48 GB total).
Setup is a Q8_K_XL quant (31.5 GB) with mmproj-F16 (0.93 GB), 200K context and an f16 KV cache, tensor split 50/50. MTP draft depth 2 gives the best acceptance at 92% on code and 68% on prose.
The speeds are medians of 3 draws at temp 0. The hybrid architecture has 48 of 64 layers as Gated DeltaNet (linear attention), with only 16 full attention layers plus the MTP head, for 17 KV-caching layers. Cold start is 32s. The split is ~1.1 GB lopsided, causing OOM risk at 220K context. User asks for optimization suggestions for dual 3090 setups.