phi4-mini:latest
OLLAMA GGUFphi3 · 3.8B · Q4_K_M
Jun 26, 2026 · Cortex-A78AE
qwen3-vl:4b-instruct
OLLAMA GGUFqwen3vl · 4.4B · Q4_K_M
Apr 20, 2026 · Apple M2 Max
Global Score
74 vs 83
Hardware Fit
98 vs 96
Quality Score
63 vs 78
Hardware
phi4-mini:latest qwen3-vl:4b-instruct
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperMac Studio
CPUCortex-A78AEApple M2 Max
Cores612
RAM7 GB96 GB
GPUIntegrated / UnknownApple M2 Max
OSUbuntu 22.04.5 LTSmacOS 26.1
Archarm64arm64
Power Modebalancedbalanced
Performance
phi4-mini:latest qwen3-vl:4b-instruct
Tokens/sec18.490.6
First chunk1078 ms159 ms
TTFT1.1 s159 ms
Load time6.4 s5.8 s
Memory usage2.9 GB42.5 GB
Memory %39%44%
HW Fit Score Breakdown
phi4-mini:latest
Speed
50/50
TTFT
20/20
Memory
28/30
qwen3-vl:4b-instruct
Speed
50/50
TTFT
20/20
Memory
26/30
Quality
phi4-mini:latest
Reasoning
13/20
Coding
11/20
Instruction
14/20
Structured
11/15
Math
5/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Adequate Math: Weak Multilingual: Strong
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
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