Qwen2.5-Coder 7B-Instruct

Q4_K_M·7B params·GGUF
checkpoint: Qwen/Qwen2.5-Coder-7B-Instruct-GGUF:q4_k_m
commit: 13fb94bfda8c
weights 4.36 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-450wchat1
146.4
1977.526ms6.64990605ms0.000 GiB
GeForce RTX 3090 · 24 GiB450 Wdrv 590
llama.cpp cuda-4f13cb7 (cuda)baseline-pl-450wcodegen1
140.5
2102.447ms6.7814763.39s0.000 GiB
GeForce RTX 3090 · 24 GiB350 Wdrv 590
llama.cpp cuda-4f13cb7 (cuda)baseline-pl-350wcodegen1
139.2
1946.347ms6.8814763.44s0.000 GiB
GeForce RTX 3090 · 24 GiB450 Wdrv 590
llama.cpp cuda-4f13cb7 (cuda)baseline-pl-450wagent1
136.6
8636.875ms6.76063372.55s0.000 GiB
GeForce RTX 3090 · 24 GiB350 Wdrv 590
llama.cpp cuda-4f13cb7 (cuda)baseline-pl-350wagent1
133.7
8530.071ms6.96063372.58s0.000 GiB
GeForce RTX 3090 · 24 GiB350 Wdrv 590
llama.cpp cuda-4f13cb7 (cuda)baseline-pl-350wchat1
132.3
1383.136ms6.84990707ms0.000 GiB
GeForce RTX 3090 · 24 GiB450 Wdrv 590
llama.cpp cuda-4f13cb7 (cuda)baseline-pl-450wrag1
125.4
8204.2104ms6.785547567ms0.000 GiB
GeForce RTX 5070 · 12 GiB250 Wdrv 595
llama.cpp b9174 (vulkan)baselinecodegen1
119.4
2100.439ms8.3815894.94s0.000 GiB
GeForce RTX 5070 · 12 GiB250 Wdrv 595
llama.cpp b9174 (vulkan)baselinechat1
117.2
1531.033ms8.34997811ms0.000 GiB
GeForce RTX 5070 · 12 GiB250 Wdrv 595
llama.cpp b9174 (vulkan)baselineagent1
114.5
3643.2130ms8.56063372.94s0.000 GiB
GeForce RTX 5070 · 12 GiB250 Wdrv 595
llama.cpp b9174 (vulkan)baselinerag1
110.5
10682.480ms8.485547698ms0.000 GiB
GeForce RTX 3090 · 24 GiB350 Wdrv 590
llama.cpp cuda-4f13cb7 (cuda)baseline-pl-350wrag1
104.9
7236.2108ms6.885547569ms0.000 GiB
GeForce RTX 3090 · 24 GiB200 Wdrv 590
llama.cpp 59778f0 (cuda)baselinechat1
88.6
1403.136ms11.049901.01s0.000 GiB
GeForce RTX 3090 · 24 GiB200 Wdrv 590
llama.cpp 59778f0 (cuda)baselinecodegen1
81.4
1697.753ms12.2814765.87s0.000 GiB
GeForce RTX 3090 · 24 GiB200 Wdrv 590
llama.cpp 59778f0 (cuda)baselineagent1
79.9
8003.376ms11.76061622.10s0.000 GiB
GeForce RTX 3090 · 24 GiB200 Wdrv 590
llama.cpp 59778f0 (cuda)baselinerag1
77.5
7234.7118ms11.485547886ms0.000 GiB
GeForce RTX 3090 · 24 GiB350 Wdrv 590
llama.cpp cuda-4f13cb7 (cuda)baseline-pl-350wagent4
63.1
147.53.82s6.96063376.82s0.000 GiB
GeForce RTX 3090 · 24 GiB450 Wdrv 590
llama.cpp cuda-4f13cb7 (cuda)baseline-pl-450wagent4
51.3
151.84.36s6.76063376.88s0.000 GiB
GeForce RTX 3090 · 24 GiB200 Wdrv 590
llama.cpp 59778f0 (cuda)baselineagent4
42.4
622.31.04s19.76062325.81s0.000 GiB
GeForce RTX 5070 · 12 GiB250 Wdrv 595
llama.cpp b9174 (vulkan)baselineagent4
40.1
234.23.89s12.46063367.76s0.000 GiB

Environment

GeForce RTX 3090 · 24 GiB
cpuAMD EPYC 7302P 16-Core Processor
gpuNVIDIA GeForce RTX 3090
archNVIDIA
vram24 GiB (system 64.0 GiB)
power350 W / 450 W max(78% cap)
pcieGen 4 x16 / Gen 4 x16 max
clocksgfx 1995/2100 MHz · mem 9501 MHz
temp40°C idle · 60°C peak
peak draw343 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
temp46°C idle · 75°C peak
peak draw426 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
GeForce RTX 5070 · 12 GiB
cpuAMD Ryzen 9 7900 12-Core Processor
gpuNVIDIA GeForce RTX 5070
archNVIDIA
vram11.94 GiB (system 30.4 GiB)
power250 W / 300 W max(83% cap)
backendllama.cpp b9174 (vulkan)
serverlemonade unknown
osCachyOS
kernel7.0.8-1-cachyos
driver595.71.05
python3.14.4
containerizedfalse
runs/cell5
warmups2
endpoint/v1/chat/completions
streamingtrue