qwen3:0.6b
OLLAMA GGUFqwen3 · 751.63M · Q4_K_M
Mar 2, 2026 · Apple M4
phi4-mini:latest
OLLAMA GGUFphi3 · 3.8B · Q4_K_M
Jun 26, 2026 · Cortex-A78AE
Global Score
73 vs 74
Hardware Fit
100 vs 98
Quality Score
62 vs 63
Hardware
qwen3:0.6b phi4-mini:latest
MachineMacBook AirNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUApple M4Cortex-A78AE
Cores106
RAM32 GB7 GB
GPUApple M4Integrated / Unknown
OSmacOS 26.3Ubuntu 22.04.5 LTS
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3:0.6b phi4-mini:latest
Tokens/sec145.218.4
First chunkN/A1078 ms
TTFT1.4 s1.1 s
Load time0.7 s6.4 s
Memory usage4.1 GB2.9 GB
Memory %13%39%
HW Fit Score Breakdown
qwen3:0.6b
Speed
40/50
TTFT
30/20
Memory
30/30
phi4-mini:latest
Speed
50/50
TTFT
20/20
Memory
28/30
Quality
qwen3:0.6b
Reasoning
14/20
Coding
3/20
Instruction
11/20
Structured
13/15
Math
13/15
Multilingual
8/10
Reasoning: Adequate Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
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
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