Qwen3.8 27B
on NVIDIA RTX 4070 Ti Super · beellama.cpp · 100,000 ctx
Summary
User reports a custom hybrid quantization that fits MTP and long context into 16 GB of VRAM, with VRAM usage of ~15.93 GB.
Setup uses an asymmetric KV cache mix of kvarn5 (K) and kvarn4 (V), with tail precision of 1024 tokens and speculative decoding with 2 draft tokens.