qwen3.8-27b-mlx
LM-STUDIO MLXqwen3_5 · 27B · 8bit
Aug 17, 2026 · Apple M5 Max
gemma-4-31b-it-mlx
LM-STUDIO MLXgemma4 · 31B · 8bit
Aug 19, 2026 · Apple M4 Max
Global Score
59 vs 85
Hardware Fit
63 vs 64
Quality Score
58 vs 94
Hardware
qwen3.8-27b-mlx gemma-4-31b-it-mlx
MachineMacBook ProMacBook Pro
CPUApple M5 MaxApple M4 Max
Cores1816
RAM64 GB128 GB
GPUApple M5 MaxApple M4 Max
OSmacOS 27.0macOS 26.5.2
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.8-27b-mlx gemma-4-31b-it-mlx
Tokens/sec18.313.6
First chunk4 ms16 ms
TTFT530 ms558 ms
Load timeN/A12.3 s
Memory usage38.5 GB0.0 GB
Memory %60%0%
HW Fit Score Breakdown
qwen3.8-27b-mlx
Speed
23/50
TTFT
20/20
Memory
20/30
gemma-4-31b-it-mlx
Speed
14/50
TTFT
20/20
Memory
30/30
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
gemma-4-31b-it-mlx
Reasoning
19/20
Coding
19/20
Instruction
18/20
Structured
15/15
Math
14/15
Multilingual
9/10
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