phi4:latest
OLLAMA GGUFphi3 · 14.7B · Q4_K_M
Sep 15, 2026 · Intel Core™ i5-14400F
Qwen3-30B:30b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Aug 24, 2026 · Intel Core™ Ultra X7 358H
Global Score
85 vs 88
Hardware Fit
100 vs 90
Quality Score
79 vs 87
Hardware
phi4:latest Qwen3-30B:30b
MachineGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4GMKtec NucBox EVO-T2S
CPUIntel Core™ i5-14400FIntel Core™ Ultra X7 358H
Cores1616
RAM32 GB64 GB
GPUNVIDIA GeForce RTX 5060 TiIntel(R) Arc(TM) B390 GPU
OSMicrosoft Windows 11 Professionnel 10.0.26200Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
phi4:latest Qwen3-30B:30b
Tokens/sec38.331.3
First chunk72 ms560 ms
TTFT72 ms560 ms
Load time6.2 s15.4 s
Memory usage9.1 GB17.7 GB
Memory %29%28%
HW Fit Score Breakdown
phi4:latest
Speed
50/50
TTFT
20/20
Memory
30/30
Qwen3-30B:30b
Speed
40/50
TTFT
20/20
Memory
30/30
Quality
phi4:latest
Reasoning
18/20
Coding
19/20
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
Qwen3-30B:30b
Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
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