Qwen3.6 27B-GGUF-Q6_K

Q6_K·27B params·GGUF
checkpoint: unsloth/Qwen3.6-27B-GGUF:Q6_K

All runs (5)

HardwareBackendShapeConc.Gen tok/sTTFTTPOT (ms)Out tokTotalVRAM Δ
GeForce RTX 3090 · 24 GiBllama.cpp 59778f0 (cuda)codegen1
15.5
364ms64.4100064.43s0.000 GiB
GeForce RTX 3090 · 24 GiBllama.cpp 59778f0 (cuda)chat1
15.3
281ms61.51006.54s0.000 GiB
GeForce RTX 3090 · 24 GiBllama.cpp 59778f0 (cuda)agent1
15.0
1.09s64.550033.25s0.000 GiB
GeForce RTX 3090 · 24 GiBllama.cpp 59778f0 (cuda)rag1
14.4
1.25s63.320013.92s0.000 GiB
GeForce RTX 3090 · 24 GiBllama.cpp 59778f0 (cuda)agent4
0.7
1.82s581.222.37s0.000 GiB

Environment

GeForce RTX 3090 · 24 GiB
cpuAMD EPYC 7302P 16-Core Processor
gpuNVIDIA GeForce RTX 3090
archNVIDIA
vram24 GiB (system 64.0 GiB)
power200 W / 450 W max(44% cap)
backendllama.cpp 59778f0 (cuda)
serverlemonade unknown
osUbuntu 24.04 LTS
kernel6.17.13-7-pve
driver590.48.01
python3.12.3
containerizedtrue
runs/cell5
warmups2
endpoint/v1/chat/completions
streamingtrue