qwen3:0.6b
OLLAMA GGUFqwen3 · 751.63M · Q4_K_M
Apr 29, 2026 · Intel Core™ i5-8350U
phi4:14b
OLLAMA GGUFphi3 · 14.7B · Q4_K_M
Mar 2, 2026 · Apple M4
Global Score
61 vs 75
Hardware Fit
85 vs 79
Quality Score
51 vs 73
Hardware
qwen3:0.6b phi4:14b
MachineLENOVO 20L7CTO1WWMacBook Air
CPUIntel Core™ i5-8350UApple M4
Cores810
RAM23 GB32 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]Apple M4
OSFedora Linux 43macOS 26.3
Archx64arm64
Power Modelow-powerbalanced
Performance
qwen3:0.6b phi4:14b
Tokens/sec27.011.0
First chunk597 msN/A
TTFT8.7 s532 ms
Load time1.8 s0.7 s
Memory usage0.9 GB13.4 GB
Memory %4%42%
HW Fit Score Breakdown
qwen3:0.6b
Speed
50/50
TTFT
5/20
Memory
30/30
phi4:14b
Speed
19/50
TTFT
30/20
Memory
30/30
Quality
qwen3:0.6b
Reasoning
14/20
Coding
0/20
Instruction
9/20
Structured
12/15
Math
9/15
Multilingual
7/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Strong Math: Adequate Multilingual: Adequate
phi4:14b
Reasoning
15/20
Coding
18/20
Instruction
10/20
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