gemma4:12b-mlx
OLLAMA GGUFJul 4, 2026 · Apple M2 Pro
qwen2.5-coder:32b
OLLAMA GGUFqwen2 · 32.8B · Q4_K_M
Jun 26, 2026 · Cortex-X925
Global Score
81 vs 78
Hardware Fit
82 vs 59
Quality Score
81 vs 86
Hardware
gemma4:12b-mlx qwen2.5-coder:32b
MachineMacBook ProNVIDIA NVIDIA_DGX_Spark
CPUApple M2 ProCortex-X925
Cores1020
RAM16 GB122 GB
GPUApple M2 ProDevice 2e12
OSmacOS 26.5Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance
Performance
gemma4:12b-mlx qwen2.5-coder:32b
Tokens/sec25.39.5
First chunk761 ms394 ms
TTFT7.7 s395 ms
Load time3.6 s72.1 s
Memory usage7.1 GB26.5 GB
Memory %44%22%
HW Fit Score Breakdown
gemma4:12b-mlx
Speed
50/50
TTFT
6/20
Memory
26/30
qwen2.5-coder:32b
Speed
9/50
TTFT
20/20
Memory
30/30
Quality
gemma4:12b-mlx
Reasoning
16/20
Coding
15/20
Instruction
12/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
qwen2.5-coder:32b
Reasoning
14/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate 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