qwen3.5:9b
OLLAMA GGUFqwen35 · 9.7B · Q4_K_M
Mar 7, 2026 · AMD Ryzen 5 5500
phi4:14b
OLLAMA GGUFphi3 · 14.7B · Q4_K_M
Jun 26, 2026 · Cortex-X925
Global Score
71 vs 77
Hardware Fit
56 vs 74
Quality Score
78 vs 78
Hardware
qwen3.5:9b phi4:14b
MachineSystem manufacturerNVIDIA NVIDIA_DGX_Spark
CPUAMD Ryzen 5 5500Cortex-X925
Cores1220
RAM16 GB122 GB
GPUNVIDIA GeForce RTX 3060Device 2e12
OSMicrosoft Windows 11 IoT Enterprise LTSC 10.0.26100Ubuntu 24.04.4 LTS
Archx64arm64
Power Modebalancedperformance
Performance
qwen3.5:9b phi4:14b
Tokens/sec5.322.9
First chunk1624 ms198 ms
TTFT1.6 s198 ms
Load time4.0 s10.3 s
Memory usage7.9 GB14.7 GB
Memory %50%12%
HW Fit Score Breakdown
qwen3.5:9b
Speed
11/50
TTFT
20/20
Memory
25/30
phi4:14b
Speed
24/50
TTFT
20/20
Memory
30/30
Quality
qwen3.5:9b
Reasoning
14/20
Coding
17/20
Instruction
12/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate 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