phi3:3.8b
OLLAMA GGUFphi3 · 3.8B · Q4_0
Mar 2, 2026 · Apple M4
qwen3:0.6b
OLLAMA GGUFqwen3 · 751.63M · Q4_K_M
Apr 29, 2026 · Intel Core™ i5-8350U
Global Score
64 vs 61
Hardware Fit
100 vs 85
Quality Score
48 vs 51
Hardware
phi3:3.8b qwen3:0.6b
MachineMacBook AirLENOVO 20L7CTO1WW
CPUApple M4Intel Core™ i5-8350U
Cores108
RAM32 GB23 GB
GPUApple M4Kaby Lake-R GT2 [UHD Graphics 620]
OSmacOS 26.3Fedora Linux 43
Archarm64x64
Power Modebalancedlow-power
Performance
phi3:3.8b qwen3:0.6b
Tokens/sec42.027.0
First chunkN/A597 ms
TTFT142 ms8.7 s
Load time1.1 s1.8 s
Memory usage16.0 GB0.9 GB
Memory %50%4%
HW Fit Score Breakdown
phi3:3.8b
Speed
40/50
TTFT
30/20
Memory
30/30
qwen3:0.6b
Speed
50/50
TTFT
5/20
Memory
30/30
Quality
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
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
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