phi-1_5
LM-STUDIO GGUFphi2 · Q8_0
Mar 6, 2026 · Intel Core™ i5-5300U
gemma3n:latest
OLLAMA GGUFgemma3n · 6.9B · Q4_K_M
Mar 6, 2026 · AMD EPYC 9654P 96-Core Processor
Global Score
28 vs 81
Hardware Fit
66 vs 100
Quality Score
11 vs 73
Hardware
phi-1_5 gemma3n:latest
MachineLENOVO 20BUS00700Supermicro AS -2015HS-TNR
CPUIntel Core™ i5-5300UAMD EPYC 9654P 96-Core Processor
Cores464
RAM16 GB128 GB
GPUIntel(R) HD Graphics 5500GH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]
OSMicrosoft Windows 10 Professionnel 10.0.19045Ubuntu 24.04.3 LTS
Archx64x64
Power Modebalancedperformance
Performance
phi-1_5 gemma3n:latest
Tokens/sec6.9108.7
First chunk3040 ms333 ms
TTFT3.0 s333 ms
Load timeN/A4.5 s
Memory usage1.4 GB8.6 GB
Memory %9%7%
HW Fit Score Breakdown
phi-1_5
Speed
24/50
TTFT
16/20
Memory
26/30
gemma3n:latest
Speed
50/50
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
gemma3n:latest
Reasoning
14/20
Coding
14/20
Instruction
14/20
Structured
14/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak 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