Qwen3.6 27B-GGUF-Q2_K

Q2_K·27B params·GGUF
checkpoint: unsloth/Qwen3.6-27B-GGUF:Q2_K

All runs (5)

HardwareBackendShapeConc.Gen tok/sTTFTTPOT (ms)Out tokTotalVRAM Δ
GeForce RTX 3090 · 24 GiBllama.cpp 59778f0 (cuda)codegen1
24.3
367ms40.9100041.14s0.010 GiB
GeForce RTX 3090 · 24 GiBllama.cpp 59778f0 (cuda)chat1
24.0
250ms38.01004.16s0.000 GiB
GeForce RTX 3090 · 24 GiBllama.cpp 59778f0 (cuda)agent1
23.7
614ms41.150021.14s0.000 GiB
GeForce RTX 3090 · 24 GiBllama.cpp 59778f0 (cuda)rag1
22.1
947ms40.32009.05s0.000 GiB
GeForce RTX 3090 · 24 GiBllama.cpp 59778f0 (cuda)agent4
11.1
4.01s77.934130.88s0.030 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