Qwen3.6 27B-GGUF-Q4_K_M
Q4_K_M·27B params·GGUF
intelligence: see on Artificial Analysis →
checkpoint:
unsloth/Qwen3.6-27B-GGUF:Q4_K_MAll runs (5)
| Hardware | Backend | Shape | Conc. | Gen tok/s ↓ | TTFT | TPOT (ms) | Out tok | Total | VRAM Δ |
|---|---|---|---|---|---|---|---|---|---|
| GeForce RTX 3090 · 24 GiB | llama.cpp 59778f0 (cuda) | codegen | 1 | 21.6 | 375ms | 45.9 | 1000 | 46.39s | 0.000 GiB |
| GeForce RTX 3090 · 24 GiB | llama.cpp 59778f0 (cuda) | chat | 1 | 21.1 | 255ms | 43.5 | 100 | 4.73s | 0.000 GiB |
| GeForce RTX 3090 · 24 GiB | llama.cpp 59778f0 (cuda) | agent | 1 | 21.1 | 626ms | 46.0 | 500 | 23.75s | 0.000 GiB |
| GeForce RTX 3090 · 24 GiB | llama.cpp 59778f0 (cuda) | rag | 1 | 20.0 | 931ms | 45.0 | 200 | 9.99s | 0.000 GiB |
| GeForce RTX 3090 · 24 GiB | llama.cpp 59778f0 (cuda) | agent | 4 | 10.0 | 3.93s | 87.5 | 341 | 33.98s | 0.040 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