Back to leaderboard

phi3:3.8b

OLLAMA GGUF

phi3 · 3.8B · Q4_0

Good

Mar 2, 2026 · Apple M4

qwen3.5-4b-mlx

LM-STUDIO MLX

qwen3_5 · 4B · 4bit

Not Rec.

Mar 6, 2026 · Apple M4 Pro

Global Score
64 vs 62
Hardware Fit
100 vs 35
Quality Score
48 vs 73

Hardware

phi3:3.8b qwen3.5-4b-mlx
MachineMacBook AirMac mini
CPUApple M4Apple M4 Pro
Cores1014
RAM32 GB64 GB
GPUApple M4Apple M4 Pro
OSmacOS 26.3macOS 15.7.4
Archarm64arm64
Power Modebalancedbalanced

Performance

phi3:3.8b qwen3.5-4b-mlx
Tokens/sec42.00.0
First chunkN/A5548 ms
TTFT142 ms5.5 s
Load time1.1 sN/A
Memory usage16.0 GB2.9 GB
Memory %50%5%

HW Fit Score Breakdown

phi3:3.8b

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

qwen3.5-4b-mlx

Speed
0/50
TTFT
6/20
Memory
29/30

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

qwen3.5-4b-mlx

Reasoning
17/20
Coding
17/20
Instruction
9/20
Structured
8/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Adequate Math: Strong Multilingual: Strong
View phi3:3.8b details | View qwen3.5-4b-mlx 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