qwen3:0.6b
OLLAMA GGUFqwen3 · 751.63M · Q4_K_M
Mar 2, 2026 · Apple M4
gemma4:12b
OLLAMA GGUFgemma4 · 11.9B · Q4_K_M
Jul 4, 2026 · Apple M2 Pro
Global Score
61 vs 89
Hardware Fit
100 vs 88
Quality Score
44 vs 89
Hardware
qwen3:0.6b gemma4:12b
MachineMacBook AirMacBook Pro
CPUApple M4Apple M2 Pro
Cores1010
RAM32 GB16 GB
GPUApple M4Apple M2 Pro
OSmacOS 26.3macOS 26.5
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3:0.6b gemma4:12b
Tokens/sec144.318.5
First chunkN/A752 ms
TTFT81 ms752 ms
Load time0.9 s6.1 s
Memory usage4.1 GB7.5 GB
Memory %13%47%
HW Fit Score Breakdown
qwen3:0.6b
Speed
40/50
TTFT
30/20
Memory
30/30
gemma4:12b
Speed
42/50
TTFT
20/20
Memory
26/30
Quality
qwen3:0.6b
Reasoning
6/20
Coding
4/20
Instruction
10/20
Structured
13/15
Math
6/15
Multilingual
5/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Weak
gemma4:12b
Reasoning
17/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
12/15
Multilingual
10/10
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