← Leaderboard
kaitchup/qwen3.6-27b

Qwen3.6-27B (MoQ GGUF)

llama.cpp 27B GeneralReasoning
Throughput
9.3t/s@ 32k
Engine
llama.cpp
Parameters
27B
Released
2026-06-12
Benchmarked
2026-06-27

Context ladder

Throughput at each benched context window (single measurement).

Context KV Throughput
@ 32k peak golden 9.3t/s

Golden profile

kaitchup-qwen3-6-27b-llama

Capabilities

generaldensellamacppggufexperimental

Why we run it

Kaitchup MoQ GGUF tiers (4.0/4.5/5.0) for llama.cpp quality/size experiments on Qwen3.6-27B.

Bench notes

golden ?/? @ 8.4 tok/s — fill~14745 — bench-agent-v2 — tool_ok=False

Benchmarked 2026-06-27
SparkBench · GB10 · single node