gemma4:e2b
OLLAMA GGUFgemma4 · 4.6B · Q4_K_M
Oct 12, 2026 · AMD Ryzen 5 5500
llama3:latest
OLLAMA GGUFllama · 8.0B · Q4_0
Mar 2, 2026 · Apple M4
Global Score
93 vs 71
Hardware Fit
100 vs 95
Quality Score
90 vs 60
Hardware
gemma4:e2b llama3:latest
MachineMicrosoft WSLMacBook Air
CPUAMD Ryzen 5 5500Apple M4
Cores1210
RAM8 GB32 GB
GPUIntegrated / UnknownApple M4
OSUbuntu 26.04.1 LTSmacOS 26.3
Archx64arm64
Power Modeunknownbalanced
Performance
gemma4:e2b llama3:latest
Tokens/sec141.222.3
First chunk94 msN/A
TTFT1.6 s295 ms
Load time18.4 s0.8 s
Memory usage0.2 GB5.6 GB
Memory %3%18%
HW Fit Score Breakdown
gemma4:e2b
Speed
50/50
TTFT
20/20
Memory
30/30
llama3:latest
Speed
35/50
TTFT
30/20
Memory
30/30
Quality
gemma4:e2b
Reasoning
18/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
15/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
llama3:latest
Reasoning
9/20
Coding
9/20
Instruction
15/20
Structured
13/15
Math
4/15
Multilingual
10/10
Reasoning: Weak Coding: Weak 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