qwen3.5-9b-mlx
LM-STUDIO MLXqwen3_5 · 9B · 4bit
Mar 12, 2026 · Apple M4 Pro
phi4:14b
OLLAMA GGUFphi3 · 14.7B · Q4_K_M
Jun 26, 2026 · Cortex-X925
Global Score
77 vs 77
Hardware Fit
67 vs 74
Quality Score
81 vs 78
Hardware
qwen3.5-9b-mlx phi4:14b
MachineMac miniNVIDIA NVIDIA_DGX_Spark
CPUApple M4 ProCortex-X925
Cores1420
RAM64 GB122 GB
GPUApple M4 ProDevice 2e12
OSmacOS 15.7.4Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance
Performance
qwen3.5-9b-mlx phi4:14b
Tokens/sec20.322.9
First chunk4216 ms198 ms
TTFT4.2 s198 ms
Load timeN/A10.3 s
Memory usage5.6 GB14.7 GB
Memory %9%12%
HW Fit Score Breakdown
qwen3.5-9b-mlx
Speed
29/50
TTFT
8/20
Memory
30/30
phi4:14b
Speed
24/50
TTFT
20/20
Memory
30/30
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
phi4:14b
Reasoning
18/20
Coding
18/20
Instruction
12/20
Structured
13/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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