Qwen3.6 27B-GGUF-Q4_K_M

Q4_K_M·27B params·GGUF
checkpoint: unsloth/Qwen3.6-27B-GGUF:Q4_K_M

All runs (5)

HardwareBackendShapeConc.Gen tok/sTTFTTPOT (ms)Out tokTotalVRAM Δ
GeForce RTX 3090 · 24 GiBllama.cpp 59778f0 (cuda)codegen1
21.6
375ms45.9100046.39s0.000 GiB
GeForce RTX 3090 · 24 GiBllama.cpp 59778f0 (cuda)chat1
21.1
255ms43.51004.73s0.000 GiB
GeForce RTX 3090 · 24 GiBllama.cpp 59778f0 (cuda)agent1
21.1
626ms46.050023.75s0.000 GiB
GeForce RTX 3090 · 24 GiBllama.cpp 59778f0 (cuda)rag1
20.0
931ms45.02009.99s0.000 GiB
GeForce RTX 3090 · 24 GiBllama.cpp 59778f0 (cuda)agent4
10.0
3.93s87.534133.98s0.040 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