llama4:scout
OLLAMA GGUFllama4 · 108.6B · Q4_K_M
Oct 3, 2026 · Cortex-X925
Gemma4-26B:26b
OLLAMA GGUFgemma4 · 25.8B · Q4_K_M
Aug 24, 2026 · Intel Core™ Ultra X7 358H
Global Score
81 vs 87
Hardware Fit
64 vs 82
Quality Score
88 vs 89
Hardware
llama4:scout Gemma4-26B:26b
MachineNVIDIA NVIDIA_DGX_SparkGMKtec NucBox EVO-T2S
CPUCortex-X925Intel Core™ Ultra X7 358H
Cores2016
RAM122 GB64 GB
GPUDevice 2e12Intel(R) Arc(TM) B390 GPU
OSUbuntu 24.04.5 LTSMicrosoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modeperformancebalanced
Performance
llama4:scout Gemma4-26B:26b
Tokens/sec19.623.4
First chunk677 ms1073 ms
TTFT677 ms1.1 s
Load time13.1 s16.0 s
Memory usage63.4 GB16.7 GB
Memory %52%26%
HW Fit Score Breakdown
llama4:scout
Speed
20/50
TTFT
20/20
Memory
24/30
Gemma4-26B:26b
Speed
32/50
TTFT
20/20
Memory
30/30
Quality
llama4:scout
Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
13/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
Gemma4-26B:26b
Reasoning
16/20
Coding
19/20
Instruction
17/20
Structured
14/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest