qwen3.5:9b
OLLAMA GGUFqwen35 · 9.7B · Q4_K_M
Mar 5, 2026 · AMD RYZEN AI MAX+ 395
phi4:14b
OLLAMA GGUFphi3 · 14.7B · Q4_K_M
Mar 2, 2026 · Apple M4
Global Score
57 vs 75
Hardware Fit
61 vs 79
Quality Score
55 vs 73
Hardware
qwen3.5:9b phi4:14b
MachineAZW GTR ProMacBook Air
CPUAMD RYZEN AI MAX+ 395Apple M4
Cores3210
RAM125 GB32 GB
GPUAMD Radeon 8060SApple M4
OSUbuntu 24.04.4 LTSmacOS 26.3
Archx64arm64
Power Modelow-powerbalanced
Performance
qwen3.5:9b phi4:14b
Tokens/sec30.311.0
First chunk205 msN/A
TTFT8.7 s532 ms
Load time5.6 s0.7 s
Memory usage18.8 GB13.4 GB
Memory %15%42%
HW Fit Score Breakdown
qwen3.5:9b
Speed
30/50
TTFT
1/20
Memory
30/30
phi4:14b
Speed
19/50
TTFT
30/20
Memory
30/30
Quality
qwen3.5:9b
Reasoning
17/20
Coding
2/20
Instruction
7/20
Structured
8/15
Math
12/15
Multilingual
9/10
Reasoning: Strong Coding: Poor Instruction Following: Weak Structured Output: Adequate Math: Strong Multilingual: Strong
phi4:14b
Reasoning
15/20
Coding
18/20
Instruction
10/20
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