← Leaderboard

Qwen3.6 35B

unsloth/qwen3.6-35b-a3b-nvfp4-fast unsloth/qwen3.6-35b-a3b-gguf on HuggingFace ↗
Q4 MoE · 3B active / 35B total vLLM Reasoning

Recipe

Profile
unsloth-qwen3-6-35b-a3b-nvfp4-fast-eugr
Engine
vLLM
Served as
qwen3.6-35b-a3b-nvfp4-fast

Run on your Spark

single node shell
spark inference up unsloth-qwen3-6-35b-a3b-nvfp4-fast-eugr

Why we run it

Golden fleet target — auto-scaffolded from recipe qwen36-q4-llama.

Bench notes

bench-v2 avg 55.6 decode tok/s (2 sessions, ~50k ctx fill, tool_ok=True)

Benchmarked 2026-07-11
SparkBench · GB10 · single node