llama4:scout
OLLAMA GGUFllama4 · 108.6B · Q4_K_M
Oct 3, 2026 · Cortex-X925
gemma4:12b
OLLAMA GGUFgemma4 · 11.9B · Q4_K_M
Nov 13, 2026 · Intel Gen Intel® Core™ i7-12700
Global Score
81 vs 86
Hardware Fit
64 vs 80
Quality Score
88 vs 89
Hardware
llama4:scout gemma4:12b
MachineNVIDIA NVIDIA_DGX_SparkASUS
CPUCortex-X925Intel Gen Intel® Core™ i7-12700
Cores2020
RAM122 GB30 GB
GPUDevice 2e12Alder Lake-S GT1 [UHD Graphics 770], NVIDIA GeForce RTX 3060
OSUbuntu 24.04.5 LTSUbuntu 26.04.1 LTS
Archarm64x64
Power Modeperformancelow-power
Performance
llama4:scout gemma4:12b
Tokens/sec19.674.4
First chunk677 ms152 ms
TTFT677 ms30.0 s
Load time13.1 s0.0 s
Memory usage63.4 GB0.8 GB
Memory %52%3%
HW Fit Score Breakdown
llama4:scout
Speed
20/50
TTFT
20/20
Memory
24/30
gemma4:12b
Speed
50/50
TTFT
0/20
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
gemma4:12b
Reasoning
18/20
Coding
15/20
Instruction
17/20
Structured
15/15
Math
14/15
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