Back to leaderboard

qwen3.5:4b-mlx

OLLAMA GGUF

nvfp4

Marginal

Aug 24, 2026 · Apple M2

phi3:3.8b

OLLAMA GGUF

phi3 · 3.8B · Q4_0

Good

Mar 2, 2026 · Apple M4

Global Score
53 vs 64
Hardware Fit
82 vs 100
Quality Score
41 vs 48

Hardware

qwen3.5:4b-mlx phi3:3.8b
MachineMac miniMacBook Air
CPUApple M2Apple M4
Cores810
RAM8 GB32 GB
GPUApple M2Apple M4
OSmacOS 26.5.2macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5:4b-mlx phi3:3.8b
Tokens/sec24.742.0
First chunk302 msN/A
TTFT7.4 s142 ms
Load time3.2 s1.1 s
Memory usage3.8 GB16.0 GB
Memory %47%50%

HW Fit Score Breakdown

qwen3.5:4b-mlx

Speed
50/50
TTFT
6/20
Memory
26/30

phi3:3.8b

Speed
40/50
TTFT
30/20
Memory
30/30

Quality

qwen3.5:4b-mlx

Reasoning
13/20
Coding
2/20
Instruction
4/20
Structured
4/15
Math
10/15
Multilingual
8/10
Reasoning: Adequate Coding: Poor Instruction Following: Poor Structured Output: Weak Math: Adequate Multilingual: Strong

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
View qwen3.5:4b-mlx details | View phi3:3.8b details

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest