qwen2.5-coder:0.5b
OLLAMA GGUFqwen2 · 494.03M · Q4_K_M
Nov 13, 2026 · Intel Core™ i5-4590T
gemma4:12b-mlx
OLLAMA GGUFAug 24, 2026 · Apple M1 Pro
Global Score
59 vs 71
Hardware Fit
100 vs 76
Quality Score
41 vs 69
Hardware
qwen2.5-coder:0.5b gemma4:12b-mlx
MachineFUJITSU ESPRIMO Q920MacBook Pro
CPUIntel Core™ i5-4590TApple M1 Pro
Cores410
RAM16 GB16 GB
GPUIntel(R) HD Graphics 4600, Microsoft Remote Display AdapterApple M1 Pro
OSMicrosoft Windows 10 Pro 10.0.19045macOS 26.6.2
Archx64arm64
Power Modebalancedbalanced
Performance
qwen2.5-coder:0.5b gemma4:12b-mlx
Tokens/sec43.725.0
First chunk290 ms787 ms
TTFT290 ms30.0 s
Load time1.4 s4.0 s
Memory usage0.9 GB7.1 GB
Memory %6%45%
HW Fit Score Breakdown
qwen2.5-coder:0.5b
Speed
50/50
TTFT
20/20
Memory
30/30
gemma4:12b-mlx
Speed
50/50
TTFT
0/20
Memory
26/30
Quality
qwen2.5-coder:0.5b
Reasoning
7/20
Coding
8/20
Instruction
10/20
Structured
10/15
Math
2/15
Multilingual
4/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Weak
gemma4:12b-mlx
Reasoning
14/20
Coding
10/20
Instruction
9/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Weak Structured Output: Strong Math: Adequate 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