qwen3.8-27b-mlx
LM-STUDIO MLXqwen3_5 · 27B · 8bit
Aug 17, 2026 · Apple M5 Max
gemma4:e4b-mlx
OLLAMA GGUFJul 7, 2026 · Apple M2 Pro
Global Score
59 vs 85
Hardware Fit
63 vs 95
Quality Score
58 vs 81
Hardware
qwen3.8-27b-mlx gemma4:e4b-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:e4b-mlx
Tokens/sec18.347.3
First chunk4 ms258 ms
TTFT530 ms258 ms
Load timeN/A5.1 s
Memory usage38.5 GB7.9 GB
Memory %60%49%
HW Fit Score Breakdown
qwen3.8-27b-mlx
Speed
23/50
TTFT
20/20
Memory
20/30
gemma4:e4b-mlx
Speed
50/50
TTFT
20/20
Memory
25/30
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:e4b-mlx
Reasoning
15/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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