Qwen3.5 27B

Q4_K_M·27B params·GGUF
reasoning
checkpoint: unsloth/Qwen3.5-27B-GGUF:Q4_K_M
commit: 3221f178a6b8
weights 15.59 GiB

All runs (20)

HardwareBackendModeShapeConc.Gen tok/sPrefill tok/sTTFTTPOT (ms)Prompt tokOut tokTotalVRAM Δ
GeForce RTX 3090 · 24 GiB450 Wdrv 590
llama.cpp cuda-4f13cb7 (cuda)baseline-pl-450wcodegen1
40.5
219.0358ms23.762100024.70s0.000 GiB
GeForce RTX 3090 · 24 GiB350 Wdrv 590
llama.cpp cuda-4f13cb7 (cuda)baseline-pl-350wcodegen1
39.8
202.4305ms24.262100025.14s0.000 GiB
GeForce RTX 3090 · 24 GiB450 Wdrv 590
llama.cpp cuda-4f13cb7 (cuda)baseline-pl-450wagent1
39.1
1180.7507ms23.759950012.79s0.000 GiB
GeForce RTX 3090 · 24 GiB350 Wdrv 590
llama.cpp cuda-4f13cb7 (cuda)baseline-pl-350wagent1
38.4
1182.5506ms24.259950013.01s0.000 GiB
GeForce RTX 3090 · 24 GiB350 Wdrv 590
llama.cpp cuda-4f13cb7 (cuda)baseline-pl-350wchat1
37.9
127.3236ms24.0301002.64s0.000 GiB
GeForce RTX 3090 · 24 GiB450 Wdrv 590
llama.cpp cuda-4f13cb7 (cuda)baseline-pl-450wchat1
37.8
116.4258ms23.4301002.65s0.000 GiB
GeForce RTX 3090 · 24 GiB350 Wdrv 590
llama.cpp cuda-4f13cb7 (cuda)baseline-pl-350wrag1
35.2
1316.8785ms24.18422005.68s0.000 GiB
GeForce RTX 3090 · 24 GiB450 Wdrv 590
llama.cpp cuda-4f13cb7 (cuda)baseline-pl-450wrag1
34.1
1311.6762ms23.68422005.86s0.000 GiB
GeForce RTX 3090 · 24 GiB200 Wdrv 590
llama.cpp 59778f0 (cuda)baselinecodegen1
21.4
199.6346ms46.362100046.81s0.000 GiB
GeForce RTX 3090 · 24 GiB200 Wdrv 590
llama.cpp 59778f0 (cuda)baselinechat1
21.2
126.7253ms43.7301004.72s0.000 GiB
GeForce RTX 3090 · 24 GiB200 Wdrv 590
llama.cpp 59778f0 (cuda)baselineagent1
20.9
980.5611ms46.559950023.89s0.000 GiB
GeForce RTX 3090 · 24 GiB200 Wdrv 590
llama.cpp 59778f0 (cuda)baselinerag1
19.8
1037.8912ms45.884220010.12s0.000 GiB
GeForce RTX 3090 · 24 GiB450 Wdrv 590
llama.cpp cuda-4f13cb7 (cuda)baseline-pl-450wagent4
16.5
41.119.29s23.859950031.61s0.000 GiB
GeForce RTX 3090 · 24 GiB350 Wdrv 590
llama.cpp cuda-4f13cb7 (cuda)baseline-pl-350wagent4
16.1
31.419.67s24.259950032.24s0.000 GiB
Strix Halo · Radeon 8060S · 128 GiB unified (96 GiB VRAM)unified
llama.cpp b1203 (rocm)baselinecodegen1
11.9
172.4417ms83.563100084.02s0.003 GiB
Strix Halo · Radeon 8060S · 128 GiB unified (96 GiB VRAM)unified
llama.cpp b1203 (rocm)baselinechat1
11.6
96.9330ms83.5311008.59s0.002 GiB
Strix Halo · Radeon 8060S · 128 GiB unified (96 GiB VRAM)unified
llama.cpp b1203 (rocm)baselineagent1
11.5
279.91.75s83.659950043.53s0.008 GiB
Strix Halo · Radeon 8060S · 128 GiB unified (96 GiB VRAM)unified
llama.cpp b1203 (rocm)baselinerag1
10.9
294.61.73s83.6100520018.39s0.005 GiB
GeForce RTX 3090 · 24 GiB200 Wdrv 590
llama.cpp 59778f0 (cuda)baselineagent4
9.7
3.91s91.534135.41s0.000 GiB
Strix Halo · Radeon 8060S · 128 GiB unified (96 GiB VRAM)unified
llama.cpp b1203 (rocm)baselineagent4
5.4
232.72.12s178.959950093.01s-0.005 GiB

Environment

GeForce RTX 3090 · 24 GiB
cpuAMD EPYC 7302P 16-Core Processor
gpuNVIDIA GeForce RTX 3090
archNVIDIA
vram24 GiB (system 64.0 GiB)
power350 W / 450 W max(78% cap)
pcieGen 4 x16 / Gen 4 x16 max
clocksgfx 1965/2100 MHz · mem 9501 MHz
temp45°C idle · 64°C peak
peak draw334 W
backendllama.cpp cuda-4f13cb7 (cuda)
serverlemonade unknown
osUbuntu 24.04 LTS
kernel6.17.13-7-pve
driverNVIDIA 590.48.01 + CUDA 13.1
libc2.39
python3.12.3
containerizedtrue
llama.cppversion: 18 (4f13cb7) built with GNU 13.3.0 for Linux x86_64
build flagsGGML_CUDA=ON CMAKE_BUILD_TYPE=Release
runs/cell5
warmups2
endpoint/v1/chat/completions
streamingtrue
GeForce RTX 3090 · 24 GiB
cpuAMD EPYC 7302P 16-Core Processor
gpuNVIDIA GeForce RTX 3090
archNVIDIA
vram24 GiB (system 64.0 GiB)
power450 W / 450 W max
pcieGen 4 x16 / Gen 4 x16 max
clocksgfx 1980/2100 MHz · mem 9501 MHz
temp40°C idle · 83°C peak
peak draw435 W
backendllama.cpp cuda-4f13cb7 (cuda)
serverlemonade unknown
osUbuntu 24.04 LTS
kernel6.17.13-7-pve
driverNVIDIA 590.48.01 + CUDA 13.1
libc2.39
python3.12.3
containerizedtrue
llama.cppversion: 18 (4f13cb7) built with GNU 13.3.0 for Linux x86_64
build flagsGGML_CUDA=ON CMAKE_BUILD_TYPE=Release
runs/cell5
warmups2
endpoint/v1/chat/completions
streamingtrue
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
Strix Halo · Radeon 8060S · 128 GiB unified (96 GiB VRAM)
cpuAMD RYZEN AI MAX+ 395 w/ Radeon 8060S
gpuAMD Radeon 8060S
archStrix Halo (gfx1151)
vram96 GiB (system 31.1 GiB, unified)
backendllama.cpp b1203 (rocm)
serverlemonade 10.4.0
osUbuntu 24.04.4 LTS
kernel7.0.2-2-pve
python3.12.3
containerizedtrue
runs/cell3
warmups1
endpoint/v1/chat/completions
streamingtrue