qwen3.5:27b
OLLAMA GGUFqwen35 · 27.8B · Q4_K_M
Apr 1, 2026 · Apple M4
gemma3:4b
OLLAMA GGUFgemma3 · 4.3B · Q4_K_M
Mar 2, 2026 · Apple M4
Global Score
4 vs 80
Hardware Fit
13 vs 100
Quality Score
0 vs 71
Hardware
qwen3.5:27b gemma3:4b
MachineMac miniMacBook Air
CPUApple M4Apple M4
Cores1010
RAM24 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.5:27b gemma3:4b
Tokens/sec3.534.6
First chunk1781 msN/A
TTFT52.0 s303 ms
Load time13.4 s1.2 s
Memory usage21.3 GB4.6 GB
Memory %89%14%
HW Fit Score Breakdown
qwen3.5:27b
Speed
7/50
TTFT
0/20
Memory
6/30
gemma3:4b
Speed
40/50
TTFT
30/20
Memory
30/30
Quality
qwen3.5:27b
Reasoning
0/20
Coding
0/20
Instruction
0/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
gemma3:4b
Reasoning
11/20
Coding
17/20
Instruction
14/20
Structured
14/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate 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