gemma4:e2b
OLLAMA GGUFgemma4 · 4.6B · Q4_K_M
Oct 12, 2026 · AMD Ryzen 5 5500
qwen3.5:4b
OLLAMA GGUFqwen35 · 4.7B · Q4_K_M
Aug 22, 2026 · Apple M1 Pro
Global Score
93 vs 69
Hardware Fit
100 vs 85
Quality Score
90 vs 62
Hardware
gemma4:e2b qwen3.5:4b
MachineMicrosoft WSLMacBook Pro
CPUAMD Ryzen 5 5500Apple M1 Pro
Cores1210
RAM8 GB16 GB
GPUIntegrated / UnknownApple M1 Pro
OSUbuntu 26.04.1 LTSmacOS 26.6.2
Archx64arm64
Power Modeunknownbalanced
Performance
gemma4:e2b qwen3.5:4b
Tokens/sec141.236.9
First chunk94 ms474 ms
TTFT1.6 s6.9 s
Load time18.4 s2.9 s
Memory usage0.2 GB5.3 GB
Memory %3%33%
HW Fit Score Breakdown
gemma4:e2b
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3.5:4b
Speed
50/50
TTFT
6/20
Memory
29/30
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
qwen3.5:4b
Reasoning
16/20
Coding
1/20
Instruction
14/20
Structured
9/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Adequate 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