gemma4:e2b
OLLAMA GGUFgemma4 · 5.1B · Q4_K_M
Aug 28, 2026 · Intel Core™ i5-10210U
gemma4:31b
OLLAMA GGUFgemma4 · 31.3B · Q4_K_M
Apr 13, 2026 · Apple M4 Max
Global Score
76 vs 76
Hardware Fit
82 vs 46
Quality Score
73 vs 89
Hardware
gemma4:e2b gemma4:31b
MachineLENOVO 20U30029MBMacBook Pro
CPUIntel Core™ i5-10210UApple M4 Max
Cores816
RAM15 GB64 GB
GPUCometLake-U GT2 [UHD Graphics]Apple M4 Max
OSPop 24.04 LTSmacOS 26.3.1
Archx64arm64
Power Modeperformancebalanced
Performance
gemma4:e2b gemma4:31b
Tokens/sec13.522.4
First chunk1270 ms565 ms
TTFT1.3 s30.0 s
Load time13.4 s6.9 s
Memory usage6.5 GB43.9 GB
Memory %42%69%
HW Fit Score Breakdown
gemma4:e2b
Speed
35/50
TTFT
20/20
Memory
27/30
gemma4:31b
Speed
30/50
TTFT
0/20
Memory
16/30
Quality
gemma4:e2b
Reasoning
10/20
Coding
15/20
Instruction
16/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
gemma4:31b
Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
14/15
Multilingual
9/10
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