qwen3:0.6b
OLLAMA GGUFqwen3 · 751.63M · Q4_K_M
Apr 29, 2026 · Intel Core™ i5-8350U
phi3:3.8b
OLLAMA GGUFphi3 · 3.8B · Q4_0
Mar 2, 2026 · Apple M4
Global Score
61 vs 64
Hardware Fit
85 vs 100
Quality Score
51 vs 48
Hardware
qwen3:0.6b phi3:3.8b
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 phi3:3.8b
Tokens/sec27.042.0
First chunk597 msN/A
TTFT8.7 s142 ms
Load time1.8 s1.1 s
Memory usage0.9 GB16.0 GB
Memory %4%50%
HW Fit Score Breakdown
qwen3:0.6b
Speed
50/50
TTFT
5/20
Memory
30/30
phi3:3.8b
Speed
40/50
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
phi3:3.8b
Reasoning
12/20
Coding
3/20
Instruction
11/20
Structured
10/15
Math
5/15
Multilingual
7/10
Reasoning: Adequate Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Weak Multilingual: Adequate
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