qwen/qwen3.6-27b
LM-STUDIO MLXqwen3_5 · 27B · 4bit
Oct 22, 2026 · Apple M1 Pro
gemma4:12b-mlx
OLLAMA GGUFJul 4, 2026 · Apple M2 Pro
Global Score
80 vs 91
Hardware Fit
56 vs 96
Quality Score
90 vs 89
Hardware
qwen/qwen3.6-27b gemma4:12b-mlx
MachineMacBook ProMacBook Pro
CPUApple M1 ProApple M2 Pro
Cores1010
RAM32 GB16 GB
GPUApple M1 ProApple M2 Pro
OSmacOS 15.6.1macOS 26.5
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen/qwen3.6-27b gemma4:12b-mlx
Tokens/sec10.824.7
First chunk16 ms610 ms
TTFT2.6 s610 ms
Load timeN/A3.6 s
Memory usage21.0 GB7.1 GB
Memory %66%45%
HW Fit Score Breakdown
qwen/qwen3.6-27b
Speed
23/50
TTFT
16/20
Memory
17/30
gemma4:12b-mlx
Speed
50/50
TTFT
20/20
Memory
26/30
Quality
qwen/qwen3.6-27b
Reasoning
18/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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