qwen3:14b
OLLAMA GGUFqwen3 · 14.8B · Q4_K_M
Mar 5, 2026 · Apple M1 Max
minimax-m2.7:cloud
OLLAMA GGUFminimax
Apr 1, 2026 · Apple M4
Global Score
58 vs 74
Hardware Fit
82 vs 34
Quality Score
48 vs 91
Hardware
qwen3:14b minimax-m2.7:cloud
MachineMacBook ProMac mini
CPUApple M1 MaxApple M4
Cores1010
RAM32 GB24 GB
GPUApple M1 MaxApple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3:14b minimax-m2.7:cloud
Tokens/sec24.40.0
First chunk294 ms7588 ms
TTFT7.9 s11.4 s
Load time3.7 s0.0 s
Memory usage13.8 GB0.7 GB
Memory %43%3%
HW Fit Score Breakdown
qwen3:14b
Speed
47/50
TTFT
5/20
Memory
30/30
minimax-m2.7:cloud
Speed
0/50
TTFT
4/20
Memory
30/30
Quality
qwen3:14b
Reasoning
13/20
Coding
6/20
Instruction
10/20
Structured
9/15
Math
2/15
Multilingual
8/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Strong
minimax-m2.7:cloud
Reasoning
19/20
Coding
18/20
Instruction
15/20
Structured
14/15
Math
15/15
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