qwen3.8-27b-mlx
LM-STUDIO MLXqwen3_5 · 27B · 8bit
Aug 17, 2026 · Apple M5 Max
gemma4:12b-mlx
OLLAMA GGUFJul 4, 2026 · Apple M2 Pro
Global Score
59 vs 91
Hardware Fit
63 vs 96
Quality Score
58 vs 89
Hardware
qwen3.8-27b-mlx gemma4:12b-mlx
MachineMacBook ProMacBook Pro
CPUApple M5 MaxApple M2 Pro
Cores1810
RAM64 GB16 GB
GPUApple M5 MaxApple M2 Pro
OSmacOS 27.0macOS 26.5
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.8-27b-mlx gemma4:12b-mlx
Tokens/sec18.324.7
First chunk4 ms610 ms
TTFT530 ms610 ms
Load timeN/A3.6 s
Memory usage38.5 GB7.1 GB
Memory %60%45%
HW Fit Score Breakdown
qwen3.8-27b-mlx
Speed
23/50
TTFT
20/20
Memory
20/30
gemma4:12b-mlx
Speed
50/50
TTFT
20/20
Memory
26/30
Quality
qwen3.8-27b-mlx
Reasoning
19/20
Coding
14/20
Instruction
6/20
Structured
1/15
Math
13/15
Multilingual
5/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak
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