phi4-mini
OLLAMA GGUFAug 28, 2026 · Intel Core™ i5-10210U
google/gemma-4-e4b
LM-STUDIO GGUFgemma4 · 7.9B · Q4_K_M
Sep 20, 2026 · AMD Ryzen 9 8940HX
Global Score
51 vs 83
Hardware Fit
46 vs 96
Quality Score
53 vs 78
Hardware
phi4-mini google/gemma-4-e4b
MachineLENOVO 20U30029MBASUSTeK COMPUTER INC. ROG Strix G16 G614PH_G614PH
CPUIntel Core™ i5-10210UAMD Ryzen 9 8940HX
Cores832
RAM15 GB15 GB
GPUCometLake-U GT2 [UHD Graphics]NVIDIA GeForce RTX 5050 Laptop GPU, AMD Radeon(TM) 610M
OSPop 24.04 LTSMicrosoft Windows 11 Home Single Language 10.0.26200
Archx64x64
Power Modeperformancebalanced
Performance
phi4-mini google/gemma-4-e4b
Tokens/sec2.635.9
First chunk5406 ms9 ms
TTFT5.4 s182 ms
Load time27.4 sN/A
Memory usage4.6 GB6.5 GB
Memory %30%43%
HW Fit Score Breakdown
phi4-mini
Speed
6/50
TTFT
10/20
Memory
30/30
google/gemma-4-e4b
Speed
49/50
TTFT
20/20
Memory
27/30
Quality
phi4-mini
Reasoning
11/20
Coding
9/20
Instruction
6/20
Structured
12/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Weak Instruction Following: Weak Structured Output: Strong Math: Weak Multilingual: Strong
google/gemma-4-e4b
Reasoning
14/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
6/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong 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