Qwen3.6 27B-GGUF-Q5_K_M

Q5_K_M·27B params·GGUF
checkpoint: unsloth/Qwen3.6-27B-GGUF:Q5_K_M

All runs (5)

HardwareBackendShapeConc.Gen tok/sTTFTTPOT (ms)Out tokTotalVRAM Δ
GeForce RTX 3090 · 24 GiBllama.cpp 59778f0 (cuda)codegen1
18.9
375ms52.4100052.77s0.000 GiB
GeForce RTX 3090 · 24 GiBllama.cpp 59778f0 (cuda)chat1
18.6
268ms50.11005.38s0.000 GiB
GeForce RTX 3090 · 24 GiBllama.cpp 59778f0 (cuda)agent1
18.2
1.16s52.750027.44s0.000 GiB
GeForce RTX 3090 · 24 GiBllama.cpp 59778f0 (cuda)rag1
17.3
1.20s51.820011.56s0.000 GiB
GeForce RTX 3090 · 24 GiBllama.cpp 59778f0 (cuda)agent4
0.6
1.50s0.012.04s0.000 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