qwen2.5-coder:7b
OLLAMA GGUFqwen2 · 7.6B · Q4_K_M
Mar 2, 2026 · Apple M4
gemma4:e4b-mlx
OLLAMA GGUFJul 7, 2026 · Apple M2 Pro
Global Score
79 vs 78
Hardware Fit
95 vs 72
Quality Score
72 vs 81
Hardware
qwen2.5-coder:7b gemma4:e4b-mlx
MachineMacBook AirMacBook Pro
CPUApple M4Apple M2 Pro
Cores1010
RAM32 GB16 GB
GPUApple M4Apple M2 Pro
OSmacOS 26.3macOS 26.5
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen2.5-coder:7b gemma4:e4b-mlx
Tokens/sec22.126.9
First chunkN/A222 ms
TTFT285 ms222 ms
Load time0.8 s0.1 s
Memory usage7.6 GB15.4 GB
Memory %24%96%
HW Fit Score Breakdown
qwen2.5-coder:7b
Speed
35/50
TTFT
30/20
Memory
30/30
gemma4:e4b-mlx
Speed
50/50
TTFT
20/20
Memory
2/30
Quality
qwen2.5-coder:7b
Reasoning
10/20
Coding
18/20
Instruction
13/20
Structured
13/15
Math
9/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
gemma4:e4b-mlx
Reasoning
14/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong 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