Back to leaderboard

qwen3.5:4b-mlx

OLLAMA GGUF

nvfp4

Marginal

Aug 24, 2026 · Apple M2

microsoft/phi-4-mini-reasoning

LM-STUDIO MLX

phi3 · 3.8B · 4bit

Good

Mar 3, 2026 · Apple M4

Global Score
53 vs 62
Hardware Fit
82 vs 99
Quality Score
41 vs 46

Hardware

qwen3.5:4b-mlx microsoft/phi-4-mi…
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 microsoft/phi-4-mi…
Tokens/sec24.740.3
First chunk302 ms289 ms
TTFT7.4 s289 ms
Load time3.2 sN/A
Memory usage3.8 GB2.0 GB
Memory %47%6%

HW Fit Score Breakdown

qwen3.5:4b-mlx

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

microsoft/phi-4-mini-re…

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

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

microsoft/phi-4-mini-re…

Reasoning
7/20
Coding
6/20
Instruction
7/20
Structured
7/15
Math
12/15
Multilingual
7/10
Reasoning: Weak Coding: Weak Instruction Following: Weak Structured Output: Weak Math: Strong Multilingual: Adequate
View qwen3.5:4b-mlx details | View microsoft/phi-4-mi… 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