qwen/qwen3.8-27b
LM-STUDIO MLXqwen3_5 · 27B · 8bit
Aug 19, 2026 · Apple M4 Max
gemma4:e4b-mlx
OLLAMA GGUFJul 7, 2026 · Apple M2 Pro
Global Score
80 vs 90
Hardware Fit
52 vs 78
Quality Score
92 vs 95
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/sec16.146.1
First chunk14 ms284 ms
TTFT5.8 s3.9 s
Load time8.5 s0.1 s
Memory usage0.0 GB10.8 GB
Memory %0%68%
HW Fit Score Breakdown
qwen/qwen3.8-27b
Speed
17/50
TTFT
5/20
Memory
30/30
gemma4:e4b-mlx
Speed
50/50
TTFT
12/20
Memory
16/30
Quality
qwen/qwen3.8-27b
Reasoning
19/20
Coding
16/20
Instruction
17/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
gemma4:e4b-mlx
Reasoning
19/20
Coding
19/20
Instruction
17/20
Structured
15/15
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