qwen3.5-9b-mlx
LM-STUDIO MLXqwen3_5 · 9B · 4bit
Mar 12, 2026 · Apple M4 Pro
gemma4:e2b-mlx
OLLAMA GGUFAug 25, 2026 · Apple M1 Pro
Global Score
77 vs 82
Hardware Fit
67 vs 99
Quality Score
81 vs 75
Hardware
qwen3.5-9b-mlx gemma4:e2b-mlx
MachineMac miniMacBook Pro
CPUApple M4 ProApple M1 Pro
Cores1410
RAM64 GB16 GB
GPUApple M4 ProApple M1 Pro
OSmacOS 15.7.4macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.5-9b-mlx gemma4:e2b-mlx
Tokens/sec20.370.4
First chunk4216 ms96 ms
TTFT4.2 s96 ms
Load timeN/A2.5 s
Memory usage5.6 GB5.7 GB
Memory %9%36%
HW Fit Score Breakdown
qwen3.5-9b-mlx
Speed
29/50
TTFT
8/20
Memory
30/30
gemma4:e2b-mlx
Speed
50/50
TTFT
20/20
Memory
29/30
Quality
qwen3.5-9b-mlx
Reasoning
15/20
Coding
18/20
Instruction
16/20
Structured
14/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
gemma4:e2b-mlx
Reasoning
14/20
Coding
14/20
Instruction
15/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak 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