Back to leaderboard

qwen3.5-2b-mlx

LM-STUDIO MLX

qwen3_5 · 2B · 4bit

Good

Mar 6, 2026 · Apple M4 Pro

phi4-mini:latest

OLLAMA GGUF

phi3 · 3.8B · Q4_K_M

Good

Jun 26, 2026 · Cortex-A78AE

Global Score
65 vs 74
Hardware Fit
88 vs 98
Quality Score
55 vs 63

Hardware

qwen3.5-2b-mlx phi4-mini:latest
MachineMac miniNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUApple M4 ProCortex-A78AE
Cores146
RAM64 GB7 GB
GPUApple M4 ProIntegrated / Unknown
OSmacOS 15.7.4Ubuntu 22.04.5 LTS
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5-2b-mlx phi4-mini:latest
Tokens/sec48.918.4
First chunk4208 ms1078 ms
TTFT4.2 s1.1 s
Load timeN/A6.4 s
Memory usage1.6 GB2.9 GB
Memory %3%39%

HW Fit Score Breakdown

qwen3.5-2b-mlx

Speed
50/50
TTFT
8/20
Memory
30/30

phi4-mini:latest

Speed
50/50
TTFT
20/20
Memory
28/30

Quality

qwen3.5-2b-mlx

Reasoning
10/20
Coding
7/20
Instruction
13/20
Structured
14/15
Math
3/15
Multilingual
8/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong

phi4-mini:latest

Reasoning
13/20
Coding
11/20
Instruction
14/20
Structured
11/15
Math
5/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Adequate Math: Weak Multilingual: Strong

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