qwen/qwen3.8-27b
LM-STUDIO MLXqwen3_5 · 27B · 4bit
Aug 18, 2026 · Apple M4 Max
gemma4:e4b-mlx
OLLAMA GGUFJul 7, 2026 · Apple M2 Pro
Global Score
87 vs 85
Hardware Fit
83 vs 95
Quality Score
88 vs 81
Hardware
qwen/qwen3.8-27b gemma4:e4b-mlx
MachineMacBook ProMacBook Pro
CPUApple M4 MaxApple M2 Pro
Cores1610
RAM128 GB16 GB
GPUApple M4 MaxApple M2 Pro
OSmacOS 26.5.2macOS 26.5
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen/qwen3.8-27b gemma4:e4b-mlx
Tokens/sec29.147.3
First chunk9 ms258 ms
TTFT650 ms258 ms
Load timeN/A5.1 s
Memory usage21.0 GB7.9 GB
Memory %16%49%
HW Fit Score Breakdown
qwen/qwen3.8-27b
Speed
33/50
TTFT
20/20
Memory
30/30
gemma4:e4b-mlx
Speed
50/50
TTFT
20/20
Memory
25/30
Quality
qwen/qwen3.8-27b
Reasoning
18/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
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