Qwen3.8 27B

on NVIDIA RTX 5090 · llama.cpp · 65,536 ctx

Sep 7, 2026

Throughput

86.2 t/s gen · 588.2 tokens/s prompt processing (prefill)Prompt processing measures input prefill speed; it does not tell you the time to first token.

VRAM reported

32 GB

Summary

User reports that DSpark GGUF for Qwen3.8 27B shows no performance improvement and is extremely memory hungry. Setup is llama.cpp with DSpark support merged in PR #25173, using a converted and quantized RadixArk/Qwen3.8-27B-DSpark GGUF, with context set to 64k to test the BF16 speculator. Draft acceptance is 0.28922 with a mean length of 3.02.

View source ↗