gemma4:e2b
OLLAMA GGUFgemma4 · 5.1B · Q4_K_M
Aug 28, 2026 · Intel Core™ i5-10210U
cogito:3b
OLLAMA GGUFllama · 3.6B · Q4_K_M
Mar 6, 2026 · Apple M4
Global Score
76 vs 67
Hardware Fit
82 vs 100
Quality Score
73 vs 53
Hardware
gemma4:e2b cogito:3b
MachineLENOVO 20U30029MBMacBook Air
CPUIntel Core™ i5-10210UApple M4
Cores810
RAM15 GB32 GB
GPUCometLake-U GT2 [UHD Graphics]Apple M4
OSPop 24.04 LTSmacOS 26.3
Archx64arm64
Power Modeperformancebalanced
Performance
gemma4:e2b cogito:3b
Tokens/sec13.545.6
First chunk1270 ms177 ms
TTFT1.3 s177 ms
Load time13.4 s0.8 s
Memory usage6.5 GB7.0 GB
Memory %42%22%
HW Fit Score Breakdown
gemma4:e2b
Speed
35/50
TTFT
20/20
Memory
27/30
cogito:3b
Speed
50/50
TTFT
20/20
Memory
30/30
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
cogito:3b
Reasoning
6/20
Coding
8/20
Instruction
13/20
Structured
15/15
Math
2/15
Multilingual
9/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor 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