phi4:latest
OLLAMA GGUFphi3 · 14.7B · Q4_K_M
Sep 15, 2026 · Intel Core™ i5-14400F
qwen/qwen3-vl-30b
LM-STUDIO GGUFqwen3vlmoe · 30B · Q4_K_M
Apr 24, 2026 · AMD Ryzen 5 5500
Global Score
85 vs 92
Hardware Fit
100 vs 95
Quality Score
79 vs 90
Hardware
phi4:latest qwen/qwen3-vl-30b
MachineGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4ASUS
CPUIntel Core™ i5-14400FAMD Ryzen 5 5500
Cores1612
RAM32 GB31 GB
GPUNVIDIA GeForce RTX 5060 TiNavi 44 [Radeon RX 9060 XT]
OSMicrosoft Windows 11 Professionnel 10.0.26200Nobara Linux 43
Archx64x64
Power Modebalancedperformance
Performance
phi4:latest qwen/qwen3-vl-30b
Tokens/sec38.324.8
First chunk72 ms11 ms
TTFT72 ms735 ms
Load time6.2 s11.7 s
Memory usage9.1 GB0.6 GB
Memory %29%2%
HW Fit Score Breakdown
phi4:latest
Speed
50/50
TTFT
20/20
Memory
30/30
qwen/qwen3-vl-30b
Speed
45/50
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
qwen/qwen3-vl-30b
Reasoning
19/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
12/15
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