Back to leaderboard

qwen3.5-2b-mlx

LM-STUDIO MLX

qwen3_5 · 2B · 8bit

Good

Mar 3, 2026 · Apple M4

gemma4:12b-mlx

OLLAMA GGUF
Not Rec.

Aug 24, 2026 · Apple M1 Pro

Global Score
70 vs 71
Hardware Fit
93 vs 76
Quality Score
60 vs 69

Hardware

qwen3.5-2b-mlx gemma4:12b-mlx
MachineMacBook AirMacBook Pro
CPUApple M4Apple M1 Pro
Cores1010
RAM32 GB16 GB
GPUApple M4Apple M1 Pro
OSmacOS 26.3macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5-2b-mlx gemma4:12b-mlx
Tokens/sec32.925.0
First chunk3096 ms787 ms
TTFT3.1 s30.0 s
Load timeN/A4.0 s
Memory usage2.5 GB7.1 GB
Memory %8%45%

HW Fit Score Breakdown

qwen3.5-2b-mlx

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

gemma4:12b-mlx

Speed
50/50
TTFT
0/20
Memory
26/30

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

gemma4:12b-mlx

Reasoning
14/20
Coding
10/20
Instruction
9/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Weak Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3.5-2b-mlx details | View gemma4:12b-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