phi4-mini:latest
OLLAMA GGUFphi3 · 3.8B · Q4_K_M
Jun 26, 2026 · Cortex-A78AE
google/gemma-4-e4b
LM-STUDIO GGUFgemma4 · Q4_K_M
Jul 7, 2026 · AMD Ryzen 7 5800H
Global Score
74 vs 62
Hardware Fit
98 vs 77
Quality Score
63 vs 55
Hardware
phi4-mini:latest google/gemma-4-e4b
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperLENOVO 82JQ
CPUCortex-A78AEAMD Ryzen 7 5800H
Cores616
RAM7 GB16 GB
GPUIntegrated / UnknownNVIDIA GeForce RTX 3060 Laptop GPU
OSUbuntu 22.04.5 LTSMicrosoft Windows 11 家庭版 中文版 10.0.26100
Archarm64x64
Power Modebalancedbalanced
Performance
phi4-mini:latest google/gemma-4-e4b
Tokens/sec18.427.6
First chunk1078 ms23 ms
TTFT1.1 s480 ms
Load time6.4 sN/A
Memory usage2.9 GB13.2 GB
Memory %39%83%
HW Fit Score Breakdown
phi4-mini:latest
Speed
50/50
TTFT
20/20
Memory
28/30
google/gemma-4-e4b
Speed
48/50
TTFT
20/20
Memory
9/30
Quality
phi4-mini:latest
Reasoning
13/20
Coding
11/20
Instruction
14/20
Structured
11/15
Math
5/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Adequate Math: Weak Multilingual: Strong
google/gemma-4-e4b
Reasoning
18/20
Coding
17/20
Instruction
5/20
Structured
3/15
Math
11/15
Multilingual
1/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Poor
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