phi3:3.8b
OLLAMA GGUFphi3 · 3.8B · Q4_0
Mar 2, 2026 · Apple M4
qwen3.5:35b
OLLAMA GGUFqwen35moe · 36.0B · Q4_K_M
Mar 7, 2026 · Intel Core™ i5-14600KF
Global Score
64 vs 77
Hardware Fit
100 vs 53
Quality Score
48 vs 87
Hardware
phi3:3.8b qwen3.5:35b
MachineMacBook AirASUS
CPUApple M4Intel Core™ i5-14600KF
Cores1020
RAM32 GB32 GB
GPUApple M4NVIDIA GeForce RTX 4070 Ti SUPER
OSmacOS 26.3Microsoft Windows 11 Famille 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
phi3:3.8b qwen3.5:35b
Tokens/sec42.016.0
First chunkN/A719 ms
TTFT142 ms719 ms
Load time1.1 s17.8 s
Memory usage16.0 GB25.0 GB
Memory %50%79%
HW Fit Score Breakdown
phi3:3.8b
Speed
40/50
TTFT
30/20
Memory
30/30
qwen3.5:35b
Speed
23/50
TTFT
20/20
Memory
10/30
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
qwen3.5:35b
Reasoning
17/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong 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