Gemma-4 26B-A4B-it
Q4_K_M·26B params·256K ctx·GGUF
visiontool-callinghottool-callingvisionllamacpp
intelligence: see on Artificial Analysis →
checkpoint:
unsloth/gemma-4-26B-A4B-it-GGUF:UD-Q4_K_Mcommit:
b68961b3c96eweights 16.82 GiB · on-disk 16.90 GiB
All runs (20)
| Hardware | Backend | Mode | Shape | Conc. | Gen tok/s ↓ | Prefill tok/s | TTFT | TPOT (ms) | Prompt tok | Out tok | Total | VRAM Δ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
GeForce RTX 3090 · 24 GiB300 Wdrv 590 | llama.cpp cuda-4f13cb7 (cuda) | baseline | codegen | 1 | 109.6 | 313.2 | 235ms | 8.5 | 71 | 1000 | 9.12s | 0.000 GiB |
GeForce RTX 3090 · 24 GiB300 Wdrv 590 | llama.cpp cuda-4f13cb7 (cuda) | baseline | chat | 1 | 104.1 | 370.0 | 103ms | 8.4 | 36 | 100 | 960ms | 0.000 GiB |
GeForce RTX 3090 · 24 GiB300 Wdrv 590 | llama.cpp cuda-4f13cb7 (cuda) | baseline | agent | 1 | 100.1 | 1229.9 | 426ms | 8.6 | 618 | 500 | 5.00s | 0.000 GiB |
GeForce RTX 3090 · 24 GiB300 Wdrv 590 | llama.cpp cuda-4f13cb7 (cuda) | baseline | rag | 1 | 84.9 | 1004.8 | 634ms | 8.6 | 853 | 200 | 2.35s | 0.000 GiB |
Strix Halo · Radeon 8060S · 128 GiB unified (96 GiB VRAM)unified | llama.cpp b8940 (vulkan) | baseline | codegen | 1 | 47.9 | 277.2 | 296ms | 20.7 | 71 | 1000 | 20.88s | 0.000 GiB |
Strix Halo · Radeon 8060S · 128 GiB unified (96 GiB VRAM)unified | llama.cpp b8940 (vulkan) | baseline | chat | 1 | 47.7 | 151.7 | 244ms | 19.2 | 37 | 100 | 2.10s | 0.001 GiB |
Strix Halo · Radeon 8060S · 128 GiB unified (96 GiB VRAM)unified | llama.cpp b8940 (vulkan) | baseline | agent | 1 | 44.8 | 744.6 | 712ms | 21.1 | 618 | 500 | 11.15s | 0.000 GiB |
Strix Halo · Radeon 8060S · 128 GiB unified (96 GiB VRAM)unified | llama.cpp b8940 (vulkan) | baseline | rag | 1 | 43.2 | 1212.2 | 590ms | 21.2 | 1012 | 200 | 4.63s | 0.000 GiB |
GeForce RTX 3090 · 24 GiB300 Wdrv 590 | llama.cpp cuda-4f13cb7 (cuda) | baseline | agent | 4 | 42.4 | 85.0 | 7.71s | 8.6 | 618 | 500 | 12.21s | 0.000 GiB |
Strix Halo · Radeon 8060S · 128 GiB unified (96 GiB VRAM)unified | llama.cpp b8940 (vulkan) | baseline | agent | 4 | 18.3 | 84.6 | 7.29s | 40.8 | 618 | 500 | 27.38s | 0.000 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)
power300 W / 450 W max(67% cap)
pcieGen 4 x16 / Gen 4 x16 max
clocksgfx 1920/2100 MHz · mem 9501 MHz
temp52°C idle · 67°C peak
peak draw295 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
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
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