← Leaderboard

Qwen3.6 35B

Q4 MoE · 3B active / 35B total vLLM Reasoning

Published evals

Vendor-card figures for qwen/qwen3.6-35b-a3b — not this pack. Not measured on this Spark.

SWE-bench Verified
73.4% Qwen model card ↗ 2026-04-21 Vendor figure; internal agent scaffold (bash + file-edit).
Terminal-Bench 2.0
51.5% Qwen launch blog ↗ 2026-04-14 Vendor figure on the 35B-A3B launch post.
SWE-bench Pro
49.5% Qwen launch blog ↗ 2026-04-14

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)

Measurement history

Benchmark runs

Recorded inference benchmark sessions for this model's profile (single run).

Date Profile Method Avg Session t/s Range Fill Tool
2026-07-11latest unsloth-qwen3-6-35b-a3b-nvfp4-fast-eugr bench-agent-v2v2.0 55.6t/s 55.5 · 55.6 55.5–55.6 ~50,000 ok
bench-v2 avg 55.6 decode tok/s (2 sessions, ~50k ctx fill, tool_ok=True)
Benchmarked 2026-07-11
SparkBench · GB10 · single node