Back to leaderboard

qwen3.5-2b-mlx

LM-STUDIO MLX

qwen3_5 · 2B · 8bit

Good

Mar 3, 2026 · Apple M4

gemma-3-27b-it-qat

LM-STUDIO MLX

gemma3 · 27B · 4bit

Good

Mar 5, 2026 · Apple M4 Pro

Global Score
70 vs 76
Hardware Fit
93 vs 51
Quality Score
60 vs 87

Hardware

qwen3.5-2b-mlx gemma-3-27b-it-qat
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

qwen3.5-2b-mlx gemma-3-27b-it-qat
Tokens/sec32.98.9
First chunk3096 ms3976 ms
TTFT3.1 s4.0 s
Load timeN/AN/A
Memory usage2.5 GB15.7 GB
Memory %8%25%

HW Fit Score Breakdown

qwen3.5-2b-mlx

Speed
50/50
TTFT
13/20
Memory
30/30

gemma-3-27b-it-qat

Speed
12/50
TTFT
9/20
Memory
30/30

Quality

qwen3.5-2b-mlx

Reasoning
11/20
Coding
9/20
Instruction
14/20
Structured
14/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong

gemma-3-27b-it-qat

Reasoning
16/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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