Gemma-4 E4B-it

Q4_K_M·4B params·128K ctx·GGUF
visiontool-callingtool-callingvisionllamacpp
checkpoint: unsloth/gemma-4-E4B-it-GGUF:Q4_K_M
commit: ce152932ac27
weights 5.56 GiB · on-disk 5.00 GiB

All runs (35)

HardwareBackendModeShapeConc.Gen tok/sPrefill tok/sTTFTTPOT (ms)Prompt tokOut tokTotalVRAM Δ
GeForce RTX 3090 · 24 GiB350 Wdrv 590
llama.cpp cuda-4f13cb7 (cuda)baseline-pl-350wchat1
137.3
538.769ms6.836100728ms0.000 GiB
GeForce RTX 3090 · 24 GiB350 Wdrv 590
llama.cpp cuda-4f13cb7 (cuda)baseline-pl-350wcodegen1
137.3
742.096ms6.97110007.29s0.010 GiB
GeForce RTX 3090 · 24 GiB450 Wdrv 590
llama.cpp cuda-4f13cb7 (cuda)baseline-pl-450wcodegen1
136.6
728.298ms6.87110007.32s0.010 GiB
GeForce RTX 3090 · 24 GiB450 Wdrv 590
llama.cpp cuda-4f13cb7 (cuda)baseline-pl-450wchat1
135.9
608.259ms6.736100736ms0.000 GiB
GeForce RTX 3090 · 24 GiB450 Wdrv 590
llama.cpp cuda-4f13cb7 (cuda)baseline-pl-450wagent1
133.4
4191.2148ms6.96185003.75s0.000 GiB
GeForce RTX 3090 · 24 GiB350 Wdrv 590
llama.cpp cuda-4f13cb7 (cuda)baseline-pl-350wagent1
129.8
4493.2138ms6.96185003.85s0.000 GiB
GeForce RTX 5070 · 12 GiB250 Wdrv 595
llama.cpp b9174 (vulkan)baselinecodegen1
126.8
1069.167ms7.87110007.89s0.000 GiB
GeForce RTX 5070 · 12 GiB250 Wdrv 595
llama.cpp b9174 (vulkan)baselinechat1
124.3
612.559ms7.736100804ms0.000 GiB
GeForce RTX 5070 · 12 GiB250 Wdrv 595
llama.cpp b9174 (vulkan)baselineagent1
123.2
10548.259ms8.06185004.06s0.000 GiB
GeForce RTX 3090 · 24 GiB350 Wdrv 590
llama.cpp cuda-4f13cb7 (cuda)baseline-pl-350wrag1
122.5
5377.9196ms6.98532001.63s0.000 GiB
GeForce RTX 5070 · 12 GiB250 Wdrv 595
llama.cpp b9174 (vulkan)baselinerag1
120.5
6792.3118ms7.98532001.66s0.000 GiB
GeForce RTX 3090 · 24 GiB450 Wdrv 590
llama.cpp cuda-4f13cb7 (cuda)baseline-pl-450wrag1
118.9
4744.5180ms6.98532001.68s0.000 GiB
GeForce RTX 3090 · 24 GiB200 Wdrv 590
llama.cpp 59778f0 (cuda)baselinechat1
118.4
545.366ms8.136100845ms0.000 GiB
GeForce RTX 3090 · 24 GiB200 Wdrv 590
llama.cpp 59778f0 (cuda)baselinecodegen1
117.2
703.3101ms8.47110008.53s0.010 GiB
GeForce RTX 3090 · 24 GiB200 Wdrv 590
llama.cpp 59778f0 (cuda)baselineagent1
111.7
3614.7171ms8.66185004.48s0.000 GiB
GeForce RTX 3090 · 24 GiB200 Wdrv 590
llama.cpp 59778f0 (cuda)baselinerag1
101.9
3051.7307ms8.48532001.96s0.000 GiB
GeForce RTX 5070 · 12 GiB250 Wdrv 595
llama.cpp b9174 (vulkan)baselineagent4
59.0
294.61.88s13.36185008.48s0.000 GiB
GeForce RTX 3090 · 24 GiB450 Wdrv 590
llama.cpp cuda-4f13cb7 (cuda)baseline-pl-450wagent4
56.1
139.45.62s6.96185009.23s0.000 GiB
GeForce RTX 3090 · 24 GiB350 Wdrv 590
llama.cpp cuda-4f13cb7 (cuda)baseline-pl-350wagent4
55.2
136.95.68s7.06185009.39s0.000 GiB
Strix Halo · Radeon 8060S · 128 GiB unified (96 GiB VRAM)unified
llama.cpp b8940 (vulkan)baselinecodegen1
53.8
457.4170ms18.571100018.58s0.000 GiB
Strix Halo · Radeon 8060S · 128 GiB unified (96 GiB VRAM)unified
llama.cpp b8940 (vulkan)baselinechat1
52.9
252.3148ms18.1371001.89s0.001 GiB
GeForce RTX 3090 · 24 GiB200 Wdrv 590
llama.cpp 59778f0 (cuda)baselineagent4
52.2
460.01.77s15.66185009.58s-0.010 GiB
Strix Halo · Radeon 8060S · 128 GiB unified (96 GiB VRAM)unified
llama.cpp b8940 (vulkan)baselineagent1
51.6
1210.8446ms18.66185009.69s0.000 GiB
Strix Halo · Radeon 8060S · 128 GiB unified (96 GiB VRAM)unified
llama.cpp b8940 (vulkan)baselinerag1
50.4
2234.5347ms18.810122003.97s0.000 GiB
Strix Halo · Radeon 8060S · 128 GiB unified (96 GiB VRAM)unified
llama.cpp b8940 (vulkan)baselineagent4
25.5
143.35.18s28.561850019.63s0.001 GiB

Environment

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 b8940 (cpu)
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
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 1980/2100 MHz · mem 9501 MHz
temp43°C idle · 62°C peak
peak draw341 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
temp53°C idle · 74°C peak
peak draw406 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
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
kernel7.0.0-1-cachyos
driver595.58.03
python3.14.4
containerizedfalse
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 b8940 (vulkan)
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