Qwen3.8-27B DFlash2
qwen/qwen3.8-27b
Qwen/Qwen3.8-27B-FP8 on HuggingFace ↗
Throughput
Decode tok/s after a fixed context fill (PBM) — same agent-style workload as bench v2.
Recipe
- Profile
- qwen-qwen3-8-27b-dflash2-eugr
- Engine
- vLLM
- Context
- 64k · fp8 KV
- Served as
- qwen3.8-27b-dflash2
- Draft
- DFlash2 · n7
Run on your Spark
single node
shell
spark inference up qwen-qwen3-8-27b-dflash2-eugr
Why we run it
Official Qwen3.8-27B FP8 (unquantized lm_head) for DFlash2 on eugr.
Bench notes
PBM 4k @ 19.8 / 50k @ 6.7 / 100k @ 4.1 tok/s — perfbench-metrics — profile=qwen-qwen3-8-27b-dflash2-eugr