phi-1_5
LM-STUDIO GGUFphi2 · Q8_0
Mar 6, 2026 · Intel Core™ i5-5300U
gemma4:12b
OLLAMA GGUFgemma4 · 11.9B · Q4_K_M
Jun 26, 2026 · Cortex-X925
Global Score
28 vs 86
Hardware Fit
66 vs 78
Quality Score
11 vs 90
Hardware
phi-1_5 gemma4:12b
MachineLENOVO 20BUS00700NVIDIA NVIDIA_DGX_Spark
CPUIntel Core™ i5-5300UCortex-X925
Cores420
RAM16 GB122 GB
GPUIntel(R) HD Graphics 5500Device 2e12
OSMicrosoft Windows 10 Professionnel 10.0.19045Ubuntu 24.04.4 LTS
Archx64arm64
Power Modebalancedperformance
Performance
phi-1_5 gemma4:12b
Tokens/sec6.926.3
First chunk3040 ms545 ms
TTFT3.0 s545 ms
Load timeN/A9.5 s
Memory usage1.4 GB8.4 GB
Memory %9%7%
HW Fit Score Breakdown
phi-1_5
Speed
24/50
TTFT
16/20
Memory
26/30
gemma4:12b
Speed
28/50
TTFT
20/20
Memory
30/30
Quality
phi-1_5
Reasoning
2/20
Coding
2/20
Instruction
3/20
Structured
0/15
Math
2/15
Multilingual
2/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
gemma4:12b
Reasoning
18/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
11/15
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