qwen3.8:27b
OLLAMA GGUFqwen35 · 27.3B · Q4_K_M
Oct 3, 2026 · Cortex-X925
gemma4:12b-mlx
OLLAMA GGUFJul 4, 2026 · Apple M2 Pro
Global Score
84 vs 91
Hardware Fit
66 vs 96
Quality Score
92 vs 89
Hardware
qwen3.8:27b gemma4:12b-mlx
MachineNVIDIA NVIDIA_DGX_SparkMacBook Pro
CPUCortex-X925Apple M2 Pro
Cores2010
RAM122 GB16 GB
GPUDevice 2e12Apple M2 Pro
OSUbuntu 24.04.5 LTSmacOS 26.5
Archarm64arm64
Power Modeperformancebalanced
Performance
qwen3.8:27b gemma4:12b-mlx
Tokens/sec29.424.7
First chunk306 ms610 ms
TTFT4.8 s610 ms
Load time5.3 s3.6 s
Memory usage16.2 GB7.1 GB
Memory %13%45%
HW Fit Score Breakdown
qwen3.8:27b
Speed
31/50
TTFT
5/20
Memory
30/30
gemma4:12b-mlx
Speed
50/50
TTFT
20/20
Memory
26/30
Quality
qwen3.8:27b
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
gemma4:12b-mlx
Reasoning
16/20
Coding
19/20
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