qwen3-vl:4b-instruct
OLLAMA GGUFqwen3vl · 4.4B · Q4_K_M
Apr 20, 2026 · Apple M2 Max
phi4:latest
OLLAMA GGUFphi3 · 14.7B · Q4_K_M
Sep 15, 2026 · Intel Core™ i5-14400F
Global Score
83 vs 85
Hardware Fit
96 vs 100
Quality Score
78 vs 79
Hardware
qwen3-vl:4b-instruct phi4:latest
MachineMac StudioGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4
CPUApple M2 MaxIntel Core™ i5-14400F
Cores1216
RAM96 GB32 GB
GPUApple M2 MaxNVIDIA GeForce RTX 5060 Ti
OSmacOS 26.1Microsoft Windows 11 Professionnel 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
qwen3-vl:4b-instruct phi4:latest
Tokens/sec90.638.3
First chunk159 ms72 ms
TTFT159 ms72 ms
Load time5.8 s6.2 s
Memory usage42.5 GB9.1 GB
Memory %44%29%
HW Fit Score Breakdown
qwen3-vl:4b-instruct
Speed
50/50
TTFT
20/20
Memory
26/30
phi4:latest
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
qwen3-vl:4b-instruct
Reasoning
14/20
Coding
16/20
Instruction
16/20
Structured
15/15
Math
8/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
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
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