qwen2.5-coder:32b
OLLAMA GGUFqwen2 · 32.8B · Q4_K_M
Jun 26, 2026 · Cortex-X925
gemma4:e4b-mlx
OLLAMA GGUFAug 24, 2026 · Apple M1 Pro
Global Score
78 vs 90
Hardware Fit
59 vs 86
Quality Score
86 vs 92
Hardware
qwen2.5-coder:32b gemma4:e4b-mlx
MachineNVIDIA NVIDIA_DGX_SparkMacBook Pro
CPUCortex-X925Apple M1 Pro
Cores2010
RAM122 GB16 GB
GPUDevice 2e12Apple M1 Pro
OSUbuntu 24.04.4 LTSmacOS 26.6.2
Archarm64arm64
Power Modeperformancebalanced
Performance
qwen2.5-coder:32b gemma4:e4b-mlx
Tokens/sec9.541.8
First chunk394 ms359 ms
TTFT395 ms4.2 s
Load time72.1 s5.1 s
Memory usage26.5 GB7.9 GB
Memory %22%49%
HW Fit Score Breakdown
qwen2.5-coder:32b
Speed
9/50
TTFT
20/20
Memory
30/30
gemma4:e4b-mlx
Speed
50/50
TTFT
11/20
Memory
25/30
Quality
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
gemma4:e4b-mlx
Reasoning
19/20
Coding
19/20
Instruction
14/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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